© 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. 110880
    Prev
    Next
    INDEX
    Explanations

    organizations and individuals

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

    pets, column vector, appreciate

    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
     snapshot
    0.48
     جانے
    0.47
     दूसरा
    0.44
     Bedarf
    0.42
    すぎて
    0.42
     q
    0.41
     adelante
    0.41
     retos
    0.40
     mutate
    0.40
    wander
    0.40
    POSITIVE LOGITS
    िट
    0.55
    Ι
    0.51
    Ό
    0.51
    ANG
    0.48
    Tight
    0.48
    s
    0.47
    ισ
    0.46
    son
    0.46
    reportBody
    0.46
    ছাড়া
    0.46
    Activations Density 0.000%

    No Known Activations