© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25580
    Prev
    Next
    INDEX
    Explanations

    volunteers, addresses, food, note (numbers)

    np_acts-logits-general · gemini-2.5-flash-lite

    recipe yield quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    <h2>
    0.54
    <b>
    0.47
    <h4>
    0.47
    <strong>
    0.44
    <h3>
    0.42
    <0x0C>
    0.40
    ()\
    0.39
     }*/
    0.38
    <h5>
    0.37
    Down
    0.37
    POSITIVE LOGITS
    </strong>
    0.53
    </b>
    0.43
    टरनेट
    0.42
    :‏
    0.42
    லாத
    0.42
     :"
    0.41
     burs
    0.39
     cull
    0.38
    anj
    0.38
     chàng
    0.38
    Activations Density 0.000%

    No Known Activations