© 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. 169340
    Prev
    Next
    INDEX
    Explanations

    invention, 4-door, making, looking

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

    content within braces or code blocks

    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
     envisaged
    0.55
     Наши
    0.54
    snapshots
    0.53
    ﾅ
    0.52
     पड़ता
    0.51
    ષ્ય
    0.51
    商品の
    0.50
     ойной
    0.50
     учета
    0.50
    宓
    0.50
    POSITIVE LOGITS
     homogen
    0.50
     bicolor
    0.48
     state
    0.47
    出了
    0.46
     civil
    0.46
     별
    0.46
     non
    0.45
     repeat
    0.43
     abstain
    0.43
    Cay
    0.41
    Activations Density 0.000%

    No Known Activations