© 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. 196316
    Prev
    Next
    INDEX
    Explanations

    annual, future, financing, available, register, schools, help

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

    attire, love, like, entry

    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
    म
    0.47
    า
    0.47
     області
    0.47
    м
    0.47
     její
    0.47
     leapt
    0.46
    ्वती
    0.46
    лети
    0.45
     dve
    0.45
     bha
    0.45
    POSITIVE LOGITS
     وظ
    0.51
    0
    0.50
    这种
    0.46
     regulars
    0.44
    ]]
    0.43
    <0xBF>
    0.41
    င်း
    0.40
    aholic
    0.40
    juvant
    0.40
    oe
    0.40
    Activations Density 0.000%

    No Known Activations