© 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. 13923
    Prev
    Next
    INDEX
    Explanations

    from Public Goods

    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
    Joan
    0.43
    hôte
    0.43
    Cogn
    0.42
    Ad
    0.42
    anen
    0.41
    บ
    0.40
    Eq
    0.39
    Cle
    0.39
    othe
    0.39
    atha
    0.38
    POSITIVE LOGITS
     cartera
    0.45
     negli
    0.42
     ▼
    0.42
     criar
    0.42
     sectoral
    0.42
     vytvá
    0.41
     multidiscipl
    0.41
     ramping
    0.40
     aggressiveness
    0.40
    니
    0.40
    Activations Density 0.000%

    No Known Activations