© 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. 106868
    Prev
    Next
    INDEX
    Explanations

    laboratory spiral, debug all, control samples

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

    fight or examine

    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
    ppers
    0.44
    phases
    0.40
    })$,
    0.39
    fitting
    0.39
    前回
    0.39
    পর্ব
    0.38
    Grat
    0.38
    }~\
    0.38
     увагу
    0.38
    <0x1D>
    0.37
    POSITIVE LOGITS
    י
    0.74
    i
    0.73
    ي
    0.68
    a
    0.55
     زیرمه
    0.53
    াও
    0.52
    iunea
    0.51
     monastic
    0.50
    ი
    0.50
     Zen
    0.50
    Activations Density 0.001%

    No Known Activations