© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2939
    Prev
    Next
    INDEX
    Explanations

    words starting with mo

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

    mochi, moisture

    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_53_width_65k_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
    ماش
    0.46
    ribusi
    0.40
    력
    0.40
    אן
    0.39
     Ballot
    0.37
     حف
    0.36
     ентитету
    0.36
    outlet
    0.36
    mayan
    0.36
     kelet
    0.36
    POSITIVE LOGITS
    >,</
    0.78
    >:</
    0.75
    >.</
    0.73
    >=</
    0.72
    >−</
    0.72
    >(</
    0.70
    >)</
    0.69
    >;</
    0.68
     fence
    0.67
    >/</
    0.67
    Activations Density 0.009%

    No Known Activations