© 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. 164195
    Prev
    Next
    INDEX
    Explanations

    services, states, or objects

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

    color, jade, bland, mild

    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
     analog
    0.58
    ㍉
    0.56
    ם
    0.55
    🩹
    0.55
     analogue
    0.54
    GraphicsUnit
    0.53
     สื
    0.53
     ана
    0.52
     sceGu
    0.52
    🈺
    0.52
    POSITIVE LOGITS
    textbf
    0.55
     Values
    0.47
    </tr>
    0.44
     .
    0.44
     Environments
    0.44
    end
    0.43
     Outcome
    0.43
    em
    0.41
     Lipid
    0.41
    os
    0.40
    Activations Density 0.000%

    No Known Activations