© 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. 186129
    Prev
    Next
    INDEX
    Explanations

    gas line

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

    Apple group control system

    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
    u
    0.58
     were
    0.56
    arm
    0.55
    up
    0.55
    and
    0.52
     and
    0.51
    men
    0.50
    a
    0.50
    ma
    0.50
    Men
    0.50
    POSITIVE LOGITS
     стекло
    0.53
     추천
    0.53
     콜
    0.52
     забезпечення
    0.52
    ȟ
    0.52
     sœur
    0.51
     공연
    0.51
     đậm
    0.50
     ако
    0.50
     ဗ
    0.50
    Activations Density 0.000%

    No Known Activations