© 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. 138009
    Prev
    Next
    INDEX
    Explanations

    accompanies or follows

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

    common words and phrases

    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
     douze
    0.53
    égalité
    0.53
     élast
    0.52
    йдз
    0.50
    ຜະລິດຕະພັນ
    0.50
    दस
    0.50
     getline
    0.48
    뭡
    0.48
     энцикло
    0.47
    Ӣ
    0.47
    POSITIVE LOGITS
     host
    0.45
    sensitive
    0.45
    spe
    0.45
    bed
    0.44
     October
    0.42
    ↵
    0.41
    或其他
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    fi
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    Activations Density 0.000%

    No Known Activations