© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64695
    Prev
    Next
    INDEX
    Explanations

    susceptible to

    np_acts-logits-general · gemini-2.5-flash-lite

    subjects that are experiencing or dealing with something, often indicated by verbs like "are", "produce", "know", or "can't".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.53
     was
    -1.44
     someone
    -1.41
     it
    -1.39
     there
    -1.34
     if
    -1.26
     for
    -1.26
     you
    -1.23
     my
    -1.21
     wasn
    -1.16
    POSITIVE LOGITS
     themselves
    3.06
     their
    2.92
    Their
    2.50
    themselves
    2.31
     leurs
    2.16
     ihren
    2.02
     Their
    1.98
     kanilang
    1.91
    their
    1.88
     их
    1.84
    Activations Density 0.151%

    No Known Activations