© 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. 62929
    Prev
    Next
    INDEX
    Explanations

    industries and regions

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

    types of items

    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
    an
    0.69
    ed
    0.59
    en
    0.53
    am
    0.52
    as
    0.52
    u
    0.49
    ers
    0.48
    ent
    0.48
    os
    0.48
    A
    0.47
    POSITIVE LOGITS
    𝟯
    0.55
     rewriting
    0.55
     ﺍﻟ
    0.54
     menonton
    0.54
     palindrome
    0.53
     intervento
    0.53
     erasing
    0.52
     cyberpunk
    0.52
     tokamak
    0.52
     saloon
    0.51
    Activations Density 0.000%

    No Known Activations