© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    concepts followed by descriptions

    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
     ശക്ത
    0.90
    ຕະ
    0.88
    ಶ್ಯ
    0.87
    <unused423>
    0.86
     Hamiltonian
    0.85
     comfortably
    0.84
    <unused2017>
    0.84
    कानेर
    0.84
    <unused718>
    0.82
     Leibn
    0.82
    POSITIVE LOGITS
     ఇలా
    0.68
     dizendo
    0.59
     takiego
    0.58
    的水
    0.56
     sådan
    0.55
     znám
    0.55
    ینی
    0.54
    indeki
    0.53
    声音
    0.53
     так
    0.52
    Activations Density 0.246%

    No Known Activations