© 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. 5755
    Prev
    Next
    INDEX
    Explanations

    ice přes

    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
     इश्
    0.82
     سەر
    0.82
     Intell
    0.81
     duen
    0.81
     &$\
    0.80
     SEXUAL
    0.79
    LoginID
    0.79
    _'.$
    0.79
    ∟
    0.79
     пайда
    0.78
    POSITIVE LOGITS
    ね
    0.58
    T
    0.54
     such
    0.53
    0.53
    No
    0.53
     :
    0.52
    :/
    0.51
    Let
    0.51
     no
    0.49
     Ou
    0.48
    Activations Density 0.101%

    No Known Activations