© 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. 84237
    Prev
    Next
    INDEX
    Explanations

    still and words following

    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
     sempre
    0.52
     завжди
    0.52
     already
    0.52
     yeniden
    0.52
     сразу
    0.51
     aina
    0.51
     nuevamente
    0.51
    又
    0.51
     всегда
    0.50
     également
    0.50
    POSITIVE LOGITS
     plenty
    0.49
    Same
    0.47
     بنفس
    0.46
     상당
    0.45
     একইভাবে
    0.45
    same
    0.42
    Plenty
    0.42
    相同的
    0.41
    substantial
    0.41
     considerable
    0.40
    Activations Density 0.041%

    No Known Activations