© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19805
    Prev
    Next
    INDEX
    Explanations

    to + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    炘
    0.53
    Dealing
    0.49
    Repeating
    0.49
     అంశ
    0.48
    वैसे
    0.48
    Obviously
    0.47
    сло
    0.46
    담당
    0.46
    יל
    0.46
    แน่นอน
    0.46
    POSITIVE LOGITS
    }{\
    0.52
     that
    0.47
     V
    0.47
    style
    0.47
     T
    0.46
     setup
    0.46
     N
    0.45
     O
    0.45
     Enfer
    0.45
     X
    0.44
    Activations Density 0.004%

    No Known Activations