© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 236800
    Prev
    Next
    INDEX
    Explanations

    business or company reports

    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
    部門
    0.46
    żą
    0.45
     yielding
    0.44
    宮
    0.44
    urring
    0.42
    熱
    0.42
    热
    0.41
    鹅
    0.41
    视为
    0.40
     skrz
    0.40
    POSITIVE LOGITS
     centímetros
    0.52
     atributos
    0.51
    atributos
    0.51
     отправи
    0.50
     adsorb
    0.49
     étoiles
    0.47
     mnoh
    0.47
     estren
    0.46
     avatars
    0.46
     centimetres
    0.45
    Activations Density 0.001%

    No Known Activations