© 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. 135578
    Prev
    Next
    INDEX
    Explanations

    and share

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

    reversed contrast or sequence

    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
    তাহার
    0.44
     R
    0.43
    iring
    0.42
     marries
    0.41
    árny
    0.40
     Rs
    0.40
     RW
    0.40
     divides
    0.40
     is
    0.40
     INC
    0.40
    POSITIVE LOGITS
    Bitter
    0.50
     deje
    0.49
    }$&$
    0.49
    Questa
    0.48
     metoda
    0.47
     laissé
    0.47
    Moss
    0.47
    牴
    0.46
    Mitt
    0.46
    Dieses
    0.46
    Activations Density 0.001%

    No Known Activations