© 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. 150808
    Prev
    Next
    INDEX
    Explanations

    children, teaching, London, obtained

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

    Magic Number, secretary problem, historically demanded

    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
     accanto
    0.45
    ックス
    0.43
     sottoline
    0.43
     nærm
    0.42
    パーク
    0.42
     블루
    0.42
    けれ
    0.41
    ᓚ
    0.41
    ші
    0.41
     montré
    0.41
    POSITIVE LOGITS
     然后
    0.45
    expires
    0.44
     जिसका
    0.42
    :*
    0.42
     जिसके
    0.42
    dur
    0.41
    ahun
    0.41
    voltage
    0.41
     voltage
    0.40
    amh
    0.40
    Activations Density 0.001%

    No Known Activations