© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    unconfirmed reports

    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
    щь
    0.69
     paljon
    0.65
     뿐
    0.62
    뿐
    0.62
     genauso
    0.60
     partout
    0.60
     gevol
    0.60
    LaunchAction
    0.59
     bientôt
    0.58
    桠
    0.58
    POSITIVE LOGITS
     believed
    2.30
     alleged
    2.13
     purported
    1.99
     allegedly
    1.99
     presumed
    1.96
     suspected
    1.93
     rumoured
    1.92
     rumored
    1.90
     supposedly
    1.89
     purportedly
    1.89
    Activations Density 2.417%

    No Known Activations