© 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. 21670
    Prev
    Next
    INDEX
    Explanations

    period followed by mil

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

    correct tense and form

    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
    h
    0.68
    a
    0.63
    he
    0.61
    it
    0.61
    em
    0.60
    en
    0.53
    im
    0.53
    am
    0.50
    aj
    0.50
    w
    0.49
    POSITIVE LOGITS
     olefins
    0.52
     সেইরূপ
    0.45
    СТ
    0.45
    CTOGRAM
    0.45
     квадра
    0.45
     setToDefault
    0.44
     LOTRAchievement
    0.43
     indecent
    0.43
     আন্দোল
    0.42
     बहुपद
    0.42
    Activations Density 0.000%

    No Known Activations