© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161199
    Prev
    Next
    INDEX
    Explanations

    depending on the contract

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

    understanding what things are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    א
    0.52
    ד
    0.52
     использова
    0.49
    т
    0.49
    是中国
    0.49
    𝗘
    0.48
    ో
    0.47
    ་
    0.46
     sacrificed
    0.46
    ন
    0.46
    POSITIVE LOGITS
    prest
    0.43
     tö
    0.42
     softening
    0.41
    proses
    0.41
     Snowden
    0.41
     streams
    0.40
    rå
    0.40
    zení
    0.40
     günst
    0.40
    gangen
    0.40
    Activations Density 0.000%

    No Known Activations