© 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. 14064
    Prev
    Next
    INDEX
    Explanations

    accredited and affiliated programs

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

    accreditation and licenses

    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
     প্রবেশের
    0.42
     adjoining
    0.41
     आवासीय
    0.41
     personale
    0.39
     अर्जित
    0.39
    斂
    0.39
     multifamily
    0.38
     Decedent
    0.38
    ത്തിലേക്ക്
    0.38
     વ્યક્તિ
    0.37
    POSITIVE LOGITS
     ర
    0.38
     वर्ल्ड
    0.37
     disasters
    0.37
    Resultado
    0.37
     значит
    0.36
    World
    0.36
    ثت
    0.35
    ógico
    0.35
    goog
    0.35
    無視
    0.35
    Activations Density 0.016%

    No Known Activations