© 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. 61087
    Prev
    Next
    INDEX
    Explanations

    type of interests

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

    character descriptions

    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
    semester
    0.56
    ք
    0.50
    genus
    0.48
    mounting
    0.48
     فوری
    0.47
    observable
    0.46
     वास्तविकता
    0.46
    jari
    0.45
    arsipkan
    0.45
    룸
    0.45
    POSITIVE LOGITS
     Officials
    0.52
    satz
    0.48
    这项
    0.46
     Wird
    0.44
     Electricity
    0.43
     Combin
    0.42
     FTC
    0.41
     Steam
    0.41
    这是
    0.41
     BSTC
    0.40
    Activations Density 0.000%

    No Known Activations