© 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. 73305
    Prev
    Next
    INDEX
    Explanations

    defined as

    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_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
     and
    -1.77
    embang
    -1.12
     In
    -1.10
     posibles
    -1.09
    __":
    -1.09
     some
    -1.09
    šní
    -1.07
     as
    -1.06
     hacer
    -1.05
    べる
    -1.05
    POSITIVE LOGITS
    Anything
    1.51
    anything
    1.48
    Either
    1.45
    任何
    1.30
     любые
    1.27
     RACING
    1.27
    ggars
    1.27
    either
    1.26
    having
    1.24
    Anyone
    1.19
    Activations Density 0.064%

    No Known Activations