© 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. 35366
    Prev
    Next
    INDEX
    Explanations

    in terms of

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

    terms of

    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
     ενός
    0.67
     μιας
    0.64
    uts
    0.56
    tts
    0.56
    m
    0.53
    utti
    0.52
    p
    0.52
    inde
    0.49
     of
    0.49
    ของการ
    0.49
    POSITIVE LOGITS
     contaminación
    0.54
     danza
    0.54
    ח
    0.54
     dificultad
    0.52
     allowable
    0.52
     tragedia
    0.52
     mídia
    0.52
    ד
    0.51
     gangguan
    0.51
     wartość
    0.51
    Activations Density 0.021%

    No Known Activations