© 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. 79130
    Prev
    Next
    INDEX
    Explanations

    along with / ability of

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

    languages and nationalities

    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
    츰
    0.47
    чках
    0.46
     intérêts
    0.44
    沾
    0.44
    편집
    0.43
    чній
    0.42
    损失
    0.42
    潘
    0.42
    рій
    0.41
    같
    0.40
    POSITIVE LOGITS
     Arab
    0.47
     வடிவமை
    0.45
     ovip
    0.44
     Mater
    0.44
     Gradient
    0.43
     Egyptian
    0.43
     Bulgarian
    0.43
     Ramon
    0.42
     Departamento
    0.42
     ಹಲವಾರು
    0.42
    Activations Density 0.001%

    No Known Activations