© 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. 27113
    Prev
    Next
    INDEX
    Explanations

    Feige designed

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

    renovations, BOY, mia

    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
    ฝ
    0.50
    ビス
    0.50
    买了
    0.42
     acheté
    0.42
     Beberapa
    0.41
     negozi
    0.41
     begge
    0.41
    怎
    0.41
     Several
    0.40
     frumo
    0.40
    POSITIVE LOGITS
    واء
    0.43
    colormap
    0.41
    ną
    0.41
    datatables
    0.40
    ／
    0.39
     حيات
    0.39
     Tons
    0.38
    LinearLayout
    0.38
    -/
    0.38
     WER
    0.38
    Activations Density 0.000%

    No Known Activations