© 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. 65048
    Prev
    Next
    INDEX
    Explanations

    product development

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

    of the, and girls, hearing me

    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
     極
    0.53
     antibiotics
    0.46
     ISP
    0.45
     antibiotic
    0.44
     substant
    0.44
    -
    0.43
     Uhuru
    0.42
     foreigners
    0.42
     ISPs
    0.41
    pless
    0.41
    POSITIVE LOGITS
    🏁
    0.51
    ورة
    0.49
    یک
    0.46
     continueRoutine
    0.46
    핼
    0.46
    ਟਰ
    0.46
    🧙
    0.45
    🧠
    0.45
     danger
    0.44
     договора
    0.44
    Activations Density 0.000%

    No Known Activations