© 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. 13731
    Prev
    Next
    INDEX
    Explanations

    warnings or statements about possibilities

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

    extraterrestrial life, domestic terrorism

    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
    Did
    0.45
    The
    0.43
    DER
    0.43
    This
    0.42
     두
    0.41
    Entry
    0.41
    Brid
    0.40
    Rel
    0.40
    Decre
    0.40
    With
    0.39
    POSITIVE LOGITS
     “‘
    0.56
     “…
    0.55
     "...
    0.55
     "'
    0.52
    ળો
    0.50
     বলেছেন
    0.49
     తాను
    0.49
     «
    0.48
     "..
    0.48
    <unused2183>
    0.48
    Activations Density 0.068%

    No Known Activations