© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 106914
    Prev
    Next
    INDEX
    Explanations

    imprecise and specific descriptions

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

    C macro syntax

    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
     with
    0.48
     on
    0.44
     -\
    0.44
     from
    0.42
     fatto
    0.42
     -
    0.41
     simulates
    0.41
    が良い
    0.41
    上で
    0.41
     representation
    0.41
    POSITIVE LOGITS
     ఉంది
    0.43
     chipping
    0.42
     თვით
    0.42
     esteemed
    0.41
     poignant
    0.41
     धमकी
    0.40
    <0x84>
    0.39
    烹
    0.39
    TempVal
    0.39
     गणेश
    0.38
    Activations Density 0.002%

    No Known Activations