© 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. 69717
    Prev
    Next
    INDEX
    Explanations

    predictions trip

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

    ruler or ruled contexts

    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
    ℝ
    0.54
    FBSDKAccessToken
    0.50
     frío
    0.50
     冷
    0.47
     আচ্ছা
    0.47
    ClearedBy
    0.46
     ตำ
    0.46
     froid
    0.45
     粉
    0.45
     shutt
    0.45
    POSITIVE LOGITS
    kaar
    0.49
     मीणा
    0.45
    ledge
    0.43
    滅
    0.43
    ەتی
    0.42
    تمع
    0.42
    築
    0.42
    徭
    0.41
    生育
    0.40
    競争
    0.40
    Activations Density 0.000%

    No Known Activations