© 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. 128402
    Prev
    Next
    INDEX
    Explanations

    banking or population details

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

    leads to possibility

    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
    )。
    0.48
    issait
    0.45
    াফ
    0.45
    െങ്കില്‍
    0.44
    ouvoir
    0.43
     of
    0.43
    🌭
    0.43
    🍼
    0.42
    ضای
    0.42
    茸
    0.42
    POSITIVE LOGITS
     Dump
    0.49
     Reichs
    0.49
     DEA
    0.48
     অবস
    0.47
     Scatter
    0.47
     bombé
    0.47
     Mendez
    0.46
     Bourbon
    0.45
     Weir
    0.45
     Scare
    0.44
    Activations Density 0.000%

    No Known Activations