© 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. 184726
    Prev
    Next
    INDEX
    Explanations

    dreams to screams

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

    additional time or steps

    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
    dayspecial
    0.44
    すべて
    0.42
     dependents
    0.42
     subordinates
    0.42
    льнявыя
    0.41
    वर्स
    0.41
     uniformed
    0.41
    ፣
    0.41
     بعدی
    0.41
    他に
    0.41
    POSITIVE LOGITS
     de
    0.50
    use
    0.45
     with
    0.44
     in
    0.44
     Catalogue
    0.44
     Bios
    0.44
     for
    0.43
     Europ
    0.42
     à
    0.41
     Music
    0.41
    Activations Density 0.003%

    No Known Activations