© 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. 69309
    Prev
    Next
    INDEX
    Explanations

    highlighting menu options

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

    included notes/sections

    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
     depre
    0.50
    登陆
    0.46
    ্ল
    0.45
    ລ
    0.44
    రుగులు
    0.44
     lát
    0.43
     tala
    0.43
     onRouteChange
    0.43
     diff
    0.43
    ગુ
    0.43
    POSITIVE LOGITS
    ي
    0.51
    いない
    0.50
     Chaplain
    0.46
     provenant
    0.44
     Stahl
    0.44
     Fractals
    0.43
     সেরে
    0.43
    ان
    0.43
     основ
    0.42
    վել
    0.42
    Activations Density 0.002%

    No Known Activations