© 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. 190660
    Prev
    Next
    INDEX
    Explanations

    assist parents

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

    creative descriptions and narratives

    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
    řen
    0.50
    árt
    0.50
    好多
    0.47
    點
    0.47
    řel
    0.46
    གྲ
    0.46
    د
    0.46
    ointed
    0.45
    áticas
    0.43
    ၻ
    0.43
    POSITIVE LOGITS
     इसमें
    0.50
    তের
    0.49
     devrait
    0.47
     eseguire
    0.47
     بی‌
    0.46
     sekä
    0.45
     должен
    0.44
    ควบคุม
    0.44
     seraient
    0.44
     மற்றும்
    0.44
    Activations Density 0.000%

    No Known Activations