© 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. 71830
    Prev
    Next
    INDEX
    Explanations

    information for investigation

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

    information or data

    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
    )&=
    0.59
    patients
    0.54
     ecz
    0.46
    ሱስ
    0.46
     मरीजों
    0.46
     лучших
    0.45
    asal
    0.44
     ადგილ
    0.44
     пациен
    0.44
     낮은
    0.44
    POSITIVE LOGITS
     information
    0.47
    BUT
    0.46
     Informationen
    0.43
     (
    0.43
    的安全
    0.43
     informatie
    0.43
     confronto
    0.43
     investigar
    0.42
     informazioni
    0.42
     haar
    0.41
    Activations Density 0.000%

    No Known Activations