© 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. 182196
    Prev
    Next
    INDEX
    Explanations

    heir, direct, exemption

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

    description of conditions

    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
    ам
    0.52
     Crore
    0.49
    4
    0.48
    lam
    0.47
     Arthritis
    0.46
    lass
    0.46
    lad
    0.46
    me
    0.45
    la
    0.45
    cu
    0.45
    POSITIVE LOGITS
     boissons
    0.47
     spéciales
    0.47
    Tact
    0.45
    tos
    0.44
     profinite
    0.44
    ValueSet
    0.43
    ባቸው
    0.43
    🥂
    0.43
     thérapeut
    0.43
    しば
    0.42
    Activations Density 0.000%

    No Known Activations