© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84669
    Prev
    Next
    INDEX
    Explanations

    words combined or followed by a related descriptor

    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_40_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
     SLASH
    0.43
     Explosion
    0.41
    hidupan
    0.40
    وا
    0.39
     contratos
    0.39
    🫤
    0.39
     explosion
    0.38
     பிரபு
    0.38
    lwjglVersion
    0.38
     واضح
    0.38
    POSITIVE LOGITS
     literate
    0.36
     teenagers
    0.34
    matig
    0.34
     regardless
    0.34
    ever
    0.33
    young
    0.33
    견
    0.33
     Toy
    0.33
     ever
    0.32
     literacy
    0.32
    Activations Density 0.000%

    No Known Activations