© 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. 209184
    Prev
    Next
    INDEX
    Explanations

    phrases and clauses

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

    joint, synapses, variety, keyword

    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
    ?}",
    0.49
    varepsilon
    0.46
     todays
    0.45
    navigator
    0.45
    ྙ
    0.44
     σαν
    0.43
     राष्ट्रपति
    0.42
    TableName
    0.42
    today
    0.42
    我が
    0.41
    POSITIVE LOGITS
     Sock
    0.51
     ampl
    0.50
    <unused339>
    0.49
    ICK
    0.49
    Sock
    0.46
     Schw
    0.46
     rose
    0.45
     create
    0.45
    ರ್
    0.45
    IPO
    0.44
    Activations Density 0.001%

    No Known Activations