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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15136
    Prev
    Next
    INDEX
    Explanations

    unique math quizzes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     முன்பு
    0.40
     the
    0.36
    Сер
    0.32
     …
    0.31
     αφού
    0.31
     ይችላሉ
    0.31
     eluted
    0.31
    揄
    0.31
     אר
    0.30
    長く
    0.30
    POSITIVE LOGITS
    (!)
    0.47
    且
    0.43
     (!)
    0.43
     hochwertige
    0.35
    ంచరీలు
    0.35
    venuti
    0.33
    ńskie
    0.33
    ņ
    0.32
    ż
    0.32
    زان
    0.32
    Activations Density 0.274%

    No Known Activations