© 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. 121421
    Prev
    Next
    INDEX
    Explanations

    links to other sites

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

    warnings, risks, and specific instructions

    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
    எம்
    0.51
    कालय
    0.50
    𒍪
    0.49
     кой
    0.47
    லின்
    0.47
    হল
    0.46
    கர்
    0.45
    ็ง
    0.45
     жак
    0.45
     कैंडी
    0.45
    POSITIVE LOGITS
     elsewhere
    0.48
     else
    0.46
     concentrated
    0.46
     bunches
    0.46
    ]
    0.45
     accidentally
    0.43
    ami
    0.42
     jednocześnie
    0.42
     other
    0.42
     concurrently
    0.41
    Activations Density 0.000%

    No Known Activations