© 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. 165386
    Prev
    Next
    INDEX
    Explanations

    publication of

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

    technical and conceptual descriptors

    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
    ných
    0.55
    漁
    0.54
    卽
    0.53
    鵬
    0.50
     möjligt
    0.49
    ם
    0.49
    𝘃
    0.49
    買
    0.49
    दिष्ट
    0.48
     appreciable
    0.48
    POSITIVE LOGITS
     Global
    0.49
    ilie
    0.49
    s
    0.43
     لانه
    0.43
    ace
    0.42
     Exceptions
    0.41
    ironolactone
    0.40
    Global
    0.40
     Katherine
    0.40
     Creature
    0.39
    Activations Density 0.001%

    No Known Activations