© 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. 46236
    Prev
    Next
    INDEX
    Explanations

    hit single

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

    hit and hi sounds

    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
     الدهون
    0.42
     arrondie
    0.41
    🜨
    0.41
     أرض
    0.41
    曷
    0.41
     cliffs
    0.40
     hospitalized
    0.40
     الاخر
    0.40
     %>'
    0.39
    Month
    0.38
    POSITIVE LOGITS
     HIT
    0.69
     хи
    0.65
    HIT
    0.62
    hid
    0.61
     히
    0.61
     hi
    0.61
     هی
    0.60
    hig
    0.57
     Hiro
    0.56
     ヒ
    0.56
    Activations Density 0.025%

    No Known Activations