© 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. 105282
    Prev
    Next
    INDEX
    Explanations

    written data, go, day

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

    sites paying

    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
    瓶
    0.46
    铛
    0.45
    塘
    0.45
    clude
    0.44
    经
    0.44
    噙
    0.42
    સ
    0.42
    几乎
    0.42
    nesdays
    0.41
    ibia
    0.41
    POSITIVE LOGITS
     metagen
    0.58
     promul
    0.56
     mutagenesis
    0.54
     interdependence
    0.52
     zrozum
    0.52
     tactile
    0.50
     pozy
    0.50
     ombre
    0.49
     เด
    0.49
     understanding
    0.49
    Activations Density 0.001%

    No Known Activations