© 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. 116355
    Prev
    Next
    INDEX
    Explanations

    community engagement

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

    technical terms and specific references

    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
    負担
    0.46
    机
    0.46
    葉
    0.45
    学校
    0.43
    >
    0.43
    アニメ
    0.42
     lel
    0.42
    Machine
    0.42
    Profession
    0.42
    //
    0.41
    POSITIVE LOGITS
     pig
    0.58
     அவரின்
    0.58
    ϕ
    0.53
    otras
    0.52
    phenylsulfanyl
    0.50
     pigment
    0.50
    pig
    0.50
    ércio
    0.50
    ost
    0.49
    dengan
    0.49
    Activations Density 0.000%

    No Known Activations