© 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-16K
    7. 12754
    Prev
    Next
    INDEX
    Explanations

    actions and objects

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

    independent nation

    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_16k_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
     Internation
    0.54
     These
    0.53
    GUARD
    0.50
    欒
    0.49
    kyt
    0.49
     Andalucía
    0.48
    ADOR
    0.47
    guard
    0.47
    These
    0.46
     Afro
    0.46
    POSITIVE LOGITS
     rozwiąz
    0.48
    ні
    0.46
    ો
    0.46
    方針
    0.45
    сіб
    0.44
     plen
    0.44
     Calcd
    0.43
    ώς
    0.42
     rationale
    0.42
     bakalım
    0.42
    Activations Density 0.001%

    No Known Activations