© 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. 196941
    Prev
    Next
    INDEX
    Explanations

    until they or cause and

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

    INST, Cause, healthy, respectful

    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
     समानार्थी
    0.57
    紵
    0.57
     puente
    0.55
     तुम्ह
    0.54
     মাহমু
    0.54
     conundrum
    0.54
     സമ
    0.53
     presenti
    0.51
     カラ
    0.49
     શબ્
    0.48
    POSITIVE LOGITS
    I
    0.66
    \
    0.56
    t
    0.52
    In
    0.49
    o
    0.49
     I
    0.47
    ST
    0.47
    cir
    0.46
    h
    0.46
    ol
    0.46
    Activations Density 0.001%

    No Known Activations