© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 35235
    Prev
    Next
    INDEX
    Explanations

    cool and then something else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    Einstellungen
    0.92
    dı
    0.92
    Você
    0.92
    ד
    0.91
    Über
    0.91
    오
    0.89
    ssä
    0.89
    Kako
    0.89
    Вот
    0.88
    장
    0.88
    POSITIVE LOGITS
     ☐
    0.88
     cool
    0.87
     ஃப
    0.84
     determ
    0.83
     astronaut
    0.83
     FSC
    0.82
     FP
    0.82
     cools
    0.82
     Cool
    0.82
     for
    0.81
    Activations Density 0.003%

    No Known Activations