© 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. 194191
    Prev
    Next
    INDEX
    Explanations

    together sincefull ofspace that

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

    health of

    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
     குழந்தைகளின்
    0.55
    🩶
    0.50
    👃
    0.48
     inherit
    0.48
     stateMutability
    0.46
     เงี้ย
    0.46
     поверхность
    0.45
     वाय
    0.45
     বয়স
    0.45
     doctrinal
    0.45
    POSITIVE LOGITS
    ﻓ
    0.52
     refugi
    0.46
    専門
    0.45
     Chopra
    0.44
    fach
    0.44
    قلال
    0.44
    合作
    0.43
    经理
    0.43
     specialized
    0.43
     López
    0.42
    Activations Density 0.000%

    No Known Activations