© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10678
    Prev
    Next
    INDEX
    Explanations

    stones grinding

    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_13_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
     కాల్
    1.11
    τ
    1.08
     skillet
    1.04
    Γ
    1.04
     ultraf
    1.03
     bland
    1.01
     istit
    1.01
     awak
    1.00
    ાર્
    1.00
    lessly
    1.00
    POSITIVE LOGITS
    )
    0.75
    ist
    0.75
    CodeDict
    0.74
    (
    0.68
    \)
    0.68
    われている
    0.67
    ப்பட்டது
    0.64
     sme
    0.64
    (()
    0.64
     we
    0.63
    Activations Density 0.000%

    No Known Activations