© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149047
    Prev
    Next
    INDEX
    Explanations

    hierarchy and inheritance

    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_29_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
     turning
    0.72
    नाइटेड
    0.66
     მო
    0.65
     stitches
    0.65
     nodes
    0.64
    тавли
    0.64
     건
    0.64
    ➺
    0.63
    ामो
    0.63
     guarant
    0.62
    POSITIVE LOGITS
     hierarchy
    3.50
     Hierarchy
    3.22
    hierarchy
    3.19
     hierarchical
    3.16
    Hier
    3.15
    Hierarchy
    3.08
     Hier
    3.05
     hierarchies
    3.04
    hier
    2.84
     hierarch
    2.72
    Activations Density 0.120%

    No Known Activations