© 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. 19065
    Prev
    Next
    INDEX
    Explanations

    hierarchy and tiers

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

    hierarchies and specific systems

    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
    РА
    0.58
    ૨
    0.53
    КА
    0.53
    не
    0.52
    ר
    0.52
    РИ
    0.51
    Ahora
    0.51
    리
    0.51
    ब
    0.50
    ת
    0.49
    POSITIVE LOGITS
     hierarch
    0.48
     Tier
    0.47
     monolayers
    0.44
     tiers
    0.43
     phylogeny
    0.43
     regions
    0.43
     Rod
    0.43
     Zhou
    0.43
     priors
    0.43
     tier
    0.43
    Activations Density 0.003%

    No Known Activations