© 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. 51501
    Prev
    Next
    INDEX
    Explanations

    press release identifier

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

    approaches jurisdiction challenges

    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
     PHYSICS
    0.45
     জের
    0.43
     EVER
    0.42
    Sequence
    0.41
    zych
    0.41
    .$;
    0.40
    éricos
    0.40
     Equity
    0.39
    Chemical
    0.39
    AVI
    0.39
    POSITIVE LOGITS
     connaissance
    0.48
     گا۔
    0.45
     nelle
    0.45
     haute
    0.45
     danno
    0.44
     baffled
    0.44
    😐
    0.44
    ependant
    0.44
     hating
    0.44
     baie
    0.44
    Activations Density 0.000%

    No Known Activations