© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14419
    Prev
    Next
    INDEX
    Explanations

    special relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    """
    2.53
    prs
    2.47
    脨
    2.34
    帑
    2.32
     PWMA
    2.30
    イッチ
    2.29
     税
    2.29
    ノート
    2.28
     accountNumber
    2.27
     fichier
    2.26
    POSITIVE LOGITS
    ‘
    1.60
    ials
    1.59
     ‘
    1.59
     '
    1.55
    ’,
    1.53
    īb
    1.53
    زیز
    1.52
    нимание
    1.50
    chae
    1.50
    iz
    1.50
    Activations Density 0.000%

    No Known Activations