© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201578
    Prev
    Next
    INDEX
    Explanations

    power and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notified
    0.53
    ט
    0.53
     MOBILE
    0.50
     FOREIGN
    0.49
    ченный
    0.48
     juridique
    0.48
    รอบ
    0.48
     პროგრამ
    0.47
    트
    0.47
    考试
    0.47
    POSITIVE LOGITS
     gi
    0.47
    0
    0.47
     pots
    0.45
    ences
    0.43
    ({\
    0.43
     rain
    0.42
     sil
    0.42
     rat
    0.42
    uf
    0.42
     perfek
    0.41
    Activations Density 0.002%

    No Known Activations