© 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. 14196
    Prev
    Next
    INDEX
    Explanations

    css properties

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

    webkit and transform properties

    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
    either
    0.44
    hora
    0.43
    다
    0.43
    aa
    0.42
    Either
    0.42
     प्र
    0.41
     নাহি
    0.41
    اً
    0.41
    textcolor
    0.40
     小
    0.40
    POSITIVE LOGITS
     eszköz
    0.45
     differentiator
    0.42
     élast
    0.42
    ність
    0.41
     bombé
    0.40
    ством
    0.40
     dünyanın
    0.40
    ходження
    0.40
     остан
    0.40
    铨
    0.40
    Activations Density 0.000%

    No Known Activations