© 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. 120376
    Prev
    Next
    INDEX
    Explanations

    eye delivery

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

    oversaw, type, together, bin, controls, weather

    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
    Butyl
    0.51
     ފ
    0.47
     ໜ
    0.47
    Bang
    0.46
    cido
    0.45
     強
    0.45
     অশ্লীল
    0.45
     יו
    0.45
    ffic
    0.45
    śli
    0.44
    POSITIVE LOGITS
    which
    0.43
    阿拉
    0.43
     coordonnées
    0.43
    ாலம்
    0.42
    比
    0.42
    ீர்கள்
    0.42
    朋友
    0.42
    のもの
    0.42
    number
    0.42
    \{\
    0.41
    Activations Density 0.000%

    No Known Activations