© 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. 34-GEMMASCOPE-RES-131K
    7. 57333
    Prev
    Next
    INDEX
    Explanations

    not applicable or available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     kandang
    -0.88
     MUST
    -0.79
    Ár
    -0.77
    Jolly
    -0.77
    úš
    -0.77
    Honorary
    -0.76
    batore
    -0.76
    romy
    -0.75
     debemos
    -0.75
     plantea
    -0.75
    POSITIVE LOGITS
     applicable
    2.11
     available
    1.55
    applicable
    1.41
     Applicable
    1.40
    Applicable
    1.38
     applicability
    1.30
     applies
    1.28
     APPLICABLE
    1.23
     relevant
    1.18
    APPLIC
    1.16
    Activations Density 0.018%

    No Known Activations