© 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. 161001
    Prev
    Next
    INDEX
    Explanations

    conjunctions and context modifiers

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

    if you like a result

    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
     generically
    0.44
     Feast
    0.43
    Cheese
    0.42
    Egypt
    0.41
     Pork
    0.41
    लाश
    0.40
    <0x9C>
    0.40
    iem
    0.40
    Metal
    0.40
     Gourmet
    0.40
    POSITIVE LOGITS
     נ
    0.58
     ס
    0.48
     اگر
    0.48
    }}$;
    0.48
     batal
    0.48
    numero
    0.48
     चढ़
    0.47
    スン
    0.46
     Wenn
    0.46
     갔
    0.45
    Activations Density 0.000%

    No Known Activations