© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70372
    Prev
    Next
    INDEX
    Explanations

    unf words, on, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    (&
    0.90
     C
    0.88
     rh
    0.88
     coerced
    0.85
    させて頂
    0.83
     electrostatic
    0.83
     linkage
    0.81
    勇
    0.81
     Hosp
    0.81
     predicted
    0.80
    POSITIVE LOGITS
    ̞
    1.85
    ตอบ
    1.77
     peces
    1.74
    ospod
    1.73
    ake
    1.66
     dioses
    1.59
     *}(
    1.56
    霁
    1.56
     otk
    1.55
    tareas
    1.55
    Activations Density 0.000%

    No Known Activations