© 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. 136765
    Prev
    Next
    INDEX
    Explanations

    level each goal both attached excited or. sender image hands destruction

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

    getting smaller and smaller

    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
    theless
    0.49
    原材料
    0.46
    VI
    0.46
    FIL
    0.45
    ～
    0.45
     angios
    0.45
    Naj
    0.43
    N
    0.43
    쎄
    0.43
    ANDO
    0.42
    POSITIVE LOGITS
     newfound
    0.48
     Ethel
    0.46
     hitter
    0.44
     Người
    0.43
     equipes
    0.42
     Team
    0.41
    लरशिप
    0.41
     reinstated
    0.41
     вновь
    0.41
     Kib
    0.41
    Activations Density 0.003%

    No Known Activations