© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3150
    Prev
    Next
    INDEX
    Explanations

    safe and effective strategies

    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
    ipennis
    1.74
    ophagy
    1.51
     isomer
    1.51
    ococcus
    1.42
    렌
    1.42
     extol
    1.36
    ogluc
    1.36
     DISCLAIMED
    1.34
    ORITY
    1.34
     ventric
    1.34
    POSITIVE LOGITS
    ]."
    1.74
    。」
    1.73
    .""
    1.69
    »).
    1.67
    下來
    1.58
    」。
    1.57
    <unused2125>
    1.57
    ]".
    1.53
    <unused2231>
    1.53
    下来的
    1.52
    Activations Density 0.088%

    No Known Activations