© 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. 195441
    Prev
    Next
    INDEX
    Explanations

    apostles preach, forums acquire, changes practice

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

    language styles and intent

    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
     juguetes
    0.41
     haircut
    0.40
     potre
    0.40
    OS
    0.39
    🦅
    0.39
    ANTED
    0.39
    IV
    0.38
     heterod
    0.38
    peas
    0.38
     বীর
    0.37
    POSITIVE LOGITS
    层面
    0.45
    ぐるみ
    0.45
    ھی
    0.44
    ції
    0.44
     રહ્યું
    0.44
    ResourceType
    0.44
    бул
    0.44
     samma
    0.43
    pendown
    0.43
    润
    0.43
    Activations Density 0.004%

    No Known Activations