© 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. 9857
    Prev
    Next
    INDEX
    Explanations

    existence, form, origin

    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
    依頼
    0.45
    빠
    0.43
     часа
    0.42
    第三方
    0.42
     निखिल
    0.42
    Rescue
    0.41
     услу
    0.41
     மீட்ப
    0.40
    subplots
    0.40
    鞣
    0.40
    POSITIVE LOGITS
     maturity
    0.46
     maturation
    0.44
     representation
    0.43
     entrance
    0.42
     self
    0.41
     consists
    0.41
     arrival
    0.41
     Representation
    0.40
     Eintritt
    0.40
     entry
    0.39
    Activations Density 0.017%

    No Known Activations