© 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. 26961
    Prev
    Next
    INDEX
    Explanations

    details about criteria

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

    you are

    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
     mutilated
    0.44
    verted
    0.43
     خالی
    0.43
    све
    0.42
     complicate
    0.42
    핍
    0.41
     друг
    0.41
    /'
    0.40
    continued
    0.40
     fruitless
    0.40
    POSITIVE LOGITS
     verantwort
    0.48
     garantiza
    0.46
     podrán
    0.46
     pomiesz
    0.46
     jednot
    0.45
     hielo
    0.45
     garantir
    0.45
     noviembre
    0.44
     القسمه
    0.44
     অর্থনীতির
    0.43
    Activations Density 0.000%

    No Known Activations