© 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. 178712
    Prev
    Next
    INDEX
    Explanations

    after listing items

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

    multiplier effect

    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
    ุ
    0.50
    辊
    0.49
     especificar
    0.47
    张
    0.47
    鼾
    0.46
    อาด
    0.45
    odora
    0.45
     nantinya
    0.45
    குழந்த
    0.44
    乾隆
    0.44
    POSITIVE LOGITS
    dfrac
    0.46
     ناحيه
    0.45
     decided
    0.45
     प्रोवाइड
    0.45
     реаги
    0.45
     مين
    0.44
     }),
    0.44
     Hire
    0.44
     acted
    0.43
     Licensing
    0.42
    Activations Density 0.001%

    No Known Activations