© 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. 95170
    Prev
    Next
    INDEX
    Explanations

    speaking up, cat. 20, provide a

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

    lavish glitter

    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
    3
    0.48
    bounding
    0.43
    ↵↵
    0.43
    6
    0.43
    card
    0.42
    gan
    0.42
     Har
    0.42
    攒
    0.42
    轨道
    0.41
    ef
    0.41
    POSITIVE LOGITS
     சிகி
    0.58
    Decedent
    0.51
    éléments
    0.51
    NONE
    0.51
    یع
    0.51
    مع
    0.50
     ইন্দো
    0.50
     入っ
    0.49
    GLIGENCE
    0.49
    INTRO
    0.49
    Activations Density 0.002%

    No Known Activations