© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 471
    Prev
    Next
    INDEX
    Explanations

    initials and names

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

    a website, a list, a voice

    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_53_width_65k_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
    ,
    0.30
     (
    0.27
    (
    0.25
    0.24
     and
    0.24
     City
    0.23
     to
    0.22
    -
    0.22
    2
    0.22
    /
    0.22
    POSITIVE LOGITS
     popOperand
    0.20
    ំនួន
    0.20
     prazer
    0.19
     nascimento
    0.19
     nameWithOwner
    0.19
     auteurs
    0.18
     polypes
    0.18
     pdelay
    0.18
    嚴重
    0.18
    𒃻
    0.18
    Activations Density 0.333%

    No Known Activations