© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1214
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line HOME command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hale
    0.66
    ๋
    0.66
    锴
    0.63
     linee
    0.61
     mh
    0.61
    ுக்
    0.61
     lecteur
    0.58
    読
    0.58
     cutting
    0.58
    Sku
    0.57
    POSITIVE LOGITS
     game
    0.68
    GoalState
    0.65
    game
    0.62
    Play
    0.61
     play
    0.61
     टेक्नोलॉजी
    0.59
     Game
    0.58
    相同
    0.58
    संच
    0.56
     Play
    0.56
    Activations Density 0.526%

    No Known Activations