© 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. 9058
    Prev
    Next
    INDEX
    Explanations

    opposites, parallels, similarity

    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
    ગવાન
    0.84
    考
    0.83
     cooled
    0.83
     <%
    0.82
     reluctance
    0.80
     tro
    0.78
     homme
    0.78
     දක්
    0.77
     способен
    0.77
     அவ
    0.76
    POSITIVE LOGITS
    overwrite
    0.85
    ን
    0.80
     newsletter
    0.80
    ".
    0.77
    mail
    0.77
    rir
    0.77
     remarks
    0.76
    お知らせ
    0.74
    rh
    0.74
    กับ
    0.74
    Activations Density 0.000%

    No Known Activations