© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5518
    Prev
    Next
    INDEX
    Explanations

    smart contracts

    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
     ભ
    0.64
    வலை
    0.64
    пень
    0.61
    bbi
    0.60
     باقی
    0.60
    िवी
    0.59
     unset
    0.58
     ιστο
    0.58
     ۋ
    0.58
    ])));
    0.58
    POSITIVE LOGITS
    Yield
    0.76
     Yield
    0.71
    yielding
    0.68
    ℠
    0.65
    Results
    0.65
     yield
    0.63
    reach
    0.63
     Results
    0.63
    함을
    0.63
     woman
    0.62
    Activations Density 0.076%

    No Known Activations