© 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. 17399
    Prev
    Next
    INDEX
    Explanations

    sequences of items or actions

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

    lists, programming, requests, questions, data, length, opportunity, different, table

    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
    ã
    0.58
    ā
    0.54
    ąg
    0.52
    ɑ
    0.51
    ľ
    0.50
    abela
    0.50
    ą
    0.50
    ır
    0.50
    anation
    0.49
    å
    0.49
    POSITIVE LOGITS
     Endo
    0.65
     Assemblies
    0.62
     Access
    0.58
     Cross
    0.55
     Oxy
    0.54
     Anth
    0.53
     assemblies
    0.52
     Ancest
    0.52
     Orange
    0.51
     Cordova
    0.51
    Activations Density 0.000%

    No Known Activations