© 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. 244260
    Prev
    Next
    INDEX
    Explanations

    need to get, 8 Yard, sofas

    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
     Кня
    0.48
     回転
    0.47
     Knob
    0.47
    csp
    0.45
     আসিল
    0.45
    纺
    0.45
    公斤
    0.45
     Institutions
    0.45
    イー
    0.45
    𒂍
    0.45
    POSITIVE LOGITS
    第六
    0.47
    ﻗ
    0.46
     dernière
    0.45
     overtaking
    0.45
    conferences
    0.45
     férias
    0.44
     série
    0.44
     dodgy
    0.44
    られています
    0.44
     appearance
    0.43
    Activations Density 0.001%

    No Known Activations