© 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. 196376
    Prev
    Next
    INDEX
    Explanations

    making or making things

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

    addressconsistentambiguous

    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
    غي
    0.46
    зира
    0.46
     tutta
    0.45
    ﻛ
    0.44
    天的
    0.44
    рата
    0.43
     içer
    0.42
    質感
    0.42
    椒
    0.42
    واء
    0.42
    POSITIVE LOGITS
     पड़
    0.49
    folg
    0.48
    mith
    0.48
    megen
    0.47
    ympt
    0.46
    redni
    0.45
     Entry
    0.45
    uc
    0.44
    requently
    0.44
     asymptotic
    0.44
    Activations Density 0.000%

    No Known Activations