© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 126368
    Prev
    Next
    INDEX
    Explanations

    spray gun, perform, wreath

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

    conversations data for training chatbots

    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
    folded
    0.47
    phobic
    0.46
     দেড়
    0.44
    Closure
    0.43
    󠁷
    0.42
     folded
    0.41
    Pip
    0.41
    Fold
    0.41
    pokemon
    0.40
    Wra
    0.40
    POSITIVE LOGITS
    T
    0.50
     motore
    0.50
     ents
    0.48
     entusi
    0.46
     tarafından
    0.45
     vorm
    0.45
     olid
    0.45
    දා
    0.45
     personaggi
    0.45
     teis
    0.45
    Activations Density 0.001%

    No Known Activations