© 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. 136712
    Prev
    Next
    INDEX
    Explanations

    roadside assistance, recovery, young

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

    accounts, activity, accessible, understand, envision

    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
    榀
    0.46
    牒
    0.45
    徝
    0.43
    চী
    0.42
    厙
    0.42
     diariamente
    0.42
    凊
    0.42
    isatie
    0.41
    ethoscope
    0.41
     Eren
    0.41
    POSITIVE LOGITS
    <()>
    0.43
    Swift
    0.42
     revitalization
    0.42
    свя
    0.42
     Milner
    0.42
     Bruins
    0.41
    سان
    0.41
    NoError
    0.41
    InRange
    0.40
     wrongful
    0.40
    Activations Density 0.005%

    No Known Activations