© 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. 99137
    Prev
    Next
    INDEX
    Explanations

    edible education

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

    expensive accommodation

    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
    0.85
     solidarity
    0.55
    ↵↵
    0.51
    0
    0.50
    ?
    0.49
     cohesive
    0.48
     ultr
    0.47
     litter
    0.46
     magnon
    0.46
    ‬
    0.46
    POSITIVE LOGITS
    sning
    0.59
    imizi
    0.54
    𝘴
    0.54
    畞
    0.53
     کھانا
    0.51
    ᚄ
    0.51
    𝓮
    0.50
    𝕋
    0.50
    ovány
    0.49
    
    0.49
    Activations Density 0.000%

    No Known Activations