© 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. 462
    Prev
    Next
    INDEX
    Explanations

    section or introductory phrases

    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
    OpportunitiesBy
    0.30
    \%,
    0.27
    equalToSuperview
    0.27
    🈶
    0.26
    LastGenOutput
    0.26
    ཋ
    0.26
    Ⴉ
    0.26
    傆
    0.26
     tenido
    0.25
    名を
    0.25
    POSITIVE LOGITS
    WHAT
    0.68
     WHAT
    0.64
    SUMMARY
    0.59
    ----------------
    0.58
     **
    0.57
    PART
    0.57
    FEATURES
    0.55
     *
    0.55
     SUMMARY
    0.54
    GENERAL
    0.53
    Activations Density 0.827%

    No Known Activations