© 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. 125846
    Prev
    Next
    INDEX
    Explanations

    4 bedrooms or advances

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

    probability of success

    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
     levelled
    0.44
     positioned
    0.43
    اا
    0.42
    ègre
    0.42
    ﺳ
    0.42
    ằ
    0.42
     разби
    0.42
    ાઇન
    0.41
    mington
    0.41
    煐
    0.41
    POSITIVE LOGITS
    द्धा
    0.49
    OB
    0.46
    ODB
    0.46
    OCUS
    0.45
     minum
    0.45
    र्वाद
    0.43
    OTHER
    0.43
    َرْ
    0.43
    REEN
    0.42
     leftover
    0.42
    Activations Density 0.001%

    No Known Activations