© 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. 34068
    Prev
    Next
    INDEX
    Explanations

    reservation of

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

    Gothic architecture, initial interest, general points

    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
     roto
    0.42
    )
    0.41
     directories
    0.41
    元
    0.39
    </strong>
    0.38
     files
    0.38
        
    0.38
    文件
    0.38
     ellas
    0.38
     naciones
    0.38
    POSITIVE LOGITS
    ר
    0.49
    ное
    0.47
     sahib
    0.47
    Р
    0.46
     certainly
    0.46
     doubtless
    0.45
    ି
    0.45
    𒉣
    0.45
    ukkig
    0.45
    𝚐
    0.45
    Activations Density 0.000%

    No Known Activations