© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2314
    Prev
    Next
    INDEX
    Explanations

    business plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    。",
    2.70
    ."—
    2.52
    .",
    2.40
    ."],
    2.39
    ;",
    2.25
    ")],
    2.22
    }.",
    2.16
    "]),
    2.11
    .},
    2.09
    '",
    2.06
    POSITIVE LOGITS
    ↵↵
    6.20
    <eos>
    3.58
    ↵↵↵↵
    3.46
    ↵↵↵
    3.32
    ↵↵↵↵↵
    2.97
    <start_of_image>
    2.83
    ↵↵↵↵↵↵↵↵
    2.74
    ↵↵↵↵↵↵
    2.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    2.41
    ↵↵↵↵↵↵↵↵↵↵↵↵
    2.37
    Activations Density 7.155%

    No Known Activations