© 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. 14191
    Prev
    Next
    INDEX
    Explanations

    multimodal capabilities

    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
    ي
    3.40
    y
    2.71
    ரள
    2.70
     oport
    2.67
     scorching
    2.62
    isValid
    2.61
    ラッピング
    2.53
    ]/*
    2.52
    டன்
    2.48
    దయ
    2.47
    POSITIVE LOGITS
    sen
    2.98
    lerim
    2.62
    مان
    2.59
    ینه
    2.58
    lers
    2.58
    ailable
    2.53
    kannt
    2.52
    ssen
    2.45
    𝚎
    2.42
    īng
    2.41
    Activations Density 0.004%

    No Known Activations