© 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. 219645
    Prev
    Next
    INDEX
    Explanations

    correspondence between entities

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

    Create, delete, review, associated with

    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
     appetizing
    0.47
     spectrophot
    0.46
     alleviating
    0.46
     nope
    0.42
     biodegrad
    0.42
     variés
    0.42
     ventures
    0.41
    稈
    0.40
     prudent
    0.40
     ataupun
    0.40
    POSITIVE LOGITS
    Contours
    0.57
    Camp
    0.52
    Create
    0.52
    Created
    0.51
    Deleted
    0.50
    Delete
    0.49
    गढ़
    0.48
    Fundamental
    0.48
    Universidad
    0.48
    Созда
    0.47
    Activations Density 0.001%

    No Known Activations