© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1359
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    Or
    1.33
    "
    1.29
    And
    1.28
    Then
    1.25
    Even
    1.21
    Want
    1.18
    Related
    1.18
    م
    1.17
    ب
    1.16
    Exactly
    1.12
    POSITIVE LOGITS
     we
    1.81
     it
    1.78
     there
    1.70
     hãy
    1.68
    omitempty
    1.64
     they
    1.60
     our
    1.49
     the
    1.48
     există
    1.47
     this
    1.41
    Activations Density 0.679%

    No Known Activations