© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    word endings like loc, aph, ie, oms, ema

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

    otherworldly concepts or states

    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
     I
    0.22
    е
    0.21
    а
    0.19
     A
    0.18
    az
    0.18
     In
    0.17
    у
    0.17
    amp
    0.17
    ;
    0.17
     provides
    0.17
    POSITIVE LOGITS
     pointillés
    0.20
     myster
    0.19
    ్వర
    0.18
     whitish
    0.18
    ตาย
    0.18
     oligodend
    0.18
     leftovers
    0.18
     solitons
    0.18
     hapl
    0.18
     sporad
    0.18
    Activations Density 0.000%

    No Known Activations