© 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. 100635
    Prev
    Next
    INDEX
    Explanations

    up to glue years

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

    pattern followed by specific words

    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
    ول
    0.48
    Bye
    0.47
    Noise
    0.46
    邡
    0.44
    UIControlState
    0.44
    ENCES
    0.43
    Objects
    0.43
     Trunk
    0.43
    Nm
    0.42
    面板
    0.41
    POSITIVE LOGITS
    and
    0.51
    reif
    0.47
    ଝ
    0.46
     ALS
    0.45
    are
    0.45
    supplied
    0.45
    als
    0.44
    point
    0.44
    reaching
    0.43
    senior
    0.43
    Activations Density 0.000%

    No Known Activations