© 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. 157154
    Prev
    Next
    INDEX
    Explanations

    cabins generally, we synthesized, salt through

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

    net carbs, debugging, reaction, air

    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
    ன்றும்
    0.47
    ומים
    0.47
    א
    0.46
    Despite
    0.46
    LIMITED
    0.45
    periods
    0.45
    despite
    0.44
    alike
    0.44
     पसंद
    0.43
    ни
    0.43
    POSITIVE LOGITS
     हैद
    0.49
     vist
    0.48
     workflows
    0.48
     workflow
    0.46
    arno
    0.44
     procesu
    0.44
    額
    0.43
     snow
    0.43
     gyors
    0.43
     contro
    0.42
    Activations Density 0.000%

    No Known Activations