© 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. 51837
    Prev
    Next
    INDEX
    Explanations

    length or size of things

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

    calculating length

    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
    兩
    0.56
     two
    0.56
    BID
    0.52
    ढ़ाई
    0.52
    two
    0.51
    three
    0.50
    t
    0.50
    𝟯
    0.50
    u
    0.49
    今日は
    0.49
    POSITIVE LOGITS
     вещей
    0.45
    specifiedByURL
    0.44
     []
    0.43
     만들
    0.43
     [])
    0.43
     Sicher
    0.42
    수한
    0.42
     배열
    0.42
     của
    0.42
     этих
    0.42
    Activations Density 0.000%

    No Known Activations