© 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. 32495
    Prev
    Next
    INDEX
    Explanations

    reporting speech and political context

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

    allow, enhance, extended, rebuild

    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
    ’
    0.52
    -
    0.49
    ’,
    0.46
    잖아요
    0.41
     Operations
    0.41
    ,
    0.41
    、
    0.40
    -,
    0.40
     Guards
    0.39
    arch
    0.39
    POSITIVE LOGITS
    nir
    0.55
     اﻻ
    0.53
    ट्रा
    0.53
    iscilla
    0.52
     lovingly
    0.51
     corz
    0.50
     వారు
    0.49
    の方は
    0.49
    𝙛
    0.49
    niejsze
    0.49
    Activations Density 0.000%

    No Known Activations