© 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. 104437
    Prev
    Next
    INDEX
    Explanations

    various words, often followed by specific punctuation or subsequent words

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

    respectful and mutual connections

    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
     theorem
    0.44
    로우
    0.44
    GREAT
    0.42
    Concat
    0.41
    arctic
    0.41
    颦
    0.40
     midday
    0.40
    ृता
    0.40
    лити
    0.40
    ับสน
    0.40
    POSITIVE LOGITS
     沒有
    0.54
     इसलिए
    0.52
     औ
    0.48
     因此
    0.48
     τις
    0.48
     நாக
    0.48
     Siempre
    0.47
     በፍ
    0.47
     इसीलिए
    0.47
     arriva
    0.46
    Activations Density 0.001%

    No Known Activations