© 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. 136085
    Prev
    Next
    INDEX
    Explanations

    incorporating into, own advantages, counting your

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

    sensory and physical states

    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
    ने
    0.52
    en
    0.48
    inge
    0.47
    eh
    0.47
     äußerst
    0.47
    厢
    0.46
    ehir
    0.46
     Presidential
    0.45
    enk
    0.44
    york
    0.44
    POSITIVE LOGITS
     dia
    0.49
    that
    0.46
    ဆ
    0.45
     Dia
    0.42
     Discussion
    0.42
    йин
    0.42
     Authorities
    0.42
    ပြီး
    0.41
    Dia
    0.41
    த்தி
    0.41
    Activations Density 0.000%

    No Known Activations