© 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. 91570
    Prev
    Next
    INDEX
    Explanations

    frame these notes

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

    structuring prompts

    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
    మ్యాచ్
    0.53
     Figur
    0.49
     Mascul
    0.49
     देवताओं
    0.49
     //-->
    0.48
    మన్
    0.48
     Generators
    0.48
     höhere
    0.48
    ائيل
    0.47
    मस्कार
    0.47
    POSITIVE LOGITS
    labelled
    0.46
     স্থ
    0.45
    explored
    0.44
    пробу
    0.43
    0.42
    ى
    0.42
    considering
    0.42
    allowing
    0.41
     роботу
    0.41
    producto
    0.40
    Activations Density 0.000%

    No Known Activations