© 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. 164042
    Prev
    Next
    INDEX
    Explanations

    defined terms or acronyms

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

    parenthetical definitions

    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
     루트
    0.52
     annihil
    0.48
     인한
    0.47
     annihilation
    0.47
     openness
    0.47
     extremism
    0.46
    ཿ
    0.46
     बदल
    0.45
    FlashValue
    0.45
     heinous
    0.45
    POSITIVE LOGITS
    ).
    0.53
    otro
    0.50
    ah
    0.48
    .)
    0.44
    )
    0.43
    ť
    0.42
    <b>
    0.40
     Qualifying
    0.40
    ag
    0.40
    otra
    0.40
    Activations Density 0.004%

    No Known Activations