© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 524
    Prev
    Next
    INDEX
    Explanations

    explaining clauses with which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ي
    1.46
     bahwa
    1.42
    л
    1.41
    ص
    1.31
    𝚖
    1.31
    𝚝
    1.27
    expanding
    1.27
     وم
    1.25
    並且
    1.21
    −−
    1.20
    POSITIVE LOGITS
     is
    2.78
     makes
    2.50
     gives
    2.34
     brings
    2.31
     means
    2.21
     aligns
    2.21
     corresponds
    2.20
     consists
    2.20
     embodies
    2.16
     translates
    2.16
    Activations Density 0.068%

    No Known Activations