© 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. 17105
    Prev
    Next
    INDEX
    Explanations

    line column numbers

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

    calculating character count

    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
     투
    0.51
    聖
    0.47
     chiếu
    0.44
     laver
    0.42
     STORIES
    0.40
    皓
    0.40
    高志森
    0.40
    觫
    0.40
    哳
    0.39
    ங்கிணை
    0.39
    POSITIVE LOGITS
     vowel
    0.52
     word
    0.50
     phrase
    0.48
     noun
    0.48
     hyphen
    0.45
     name
    0.44
     Programming
    0.42
     demonstrated
    0.42
     consonant
    0.42
    word
    0.42
    Activations Density 0.001%

    No Known Activations