© 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. 121003
    Prev
    Next
    INDEX
    Explanations

    specific units or measures

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

    version identifier

    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
     بهذه
    0.49
     مكون
    0.47
     нему
    0.46
    ложен
    0.45
    凤
    0.44
     للع
    0.44
    patients
    0.43
    года
    0.43
     الهواء
    0.42
    Curve
    0.42
    POSITIVE LOGITS
    शनी
    0.51
     matemáticas
    0.48
    小学校
    0.45
     Toán
    0.45
     PICK
    0.45
     Hala
    0.44
     Matemat
    0.44
    🐄
    0.44
    レディース
    0.43
     nariz
    0.43
    Activations Density 0.000%

    No Known Activations