© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7590
    Prev
    Next
    INDEX
    Explanations

    local treatment

    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
     läuft
    1.32
    mic
    1.31
    iap
    1.25
     dov
    1.23
     dage
    1.23
    iac
    1.21
    }_
    1.21
    adr
    1.17
    IRI
    1.16
    }-
    1.15
    POSITIVE LOGITS
     Native
    1.51
     shortest
    1.49
    upe
    1.44
    shortest
    1.42
     Yak
    1.42
    ث
    1.42
     sát
    1.41
    تی
    1.40
    कर
    1.40
     Natives
    1.39
    Activations Density 0.098%

    No Known Activations