© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158013
    Prev
    Next
    INDEX
    Explanations

    free download, plan lessons, cultures left

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

    affects scarcity, humidity, shortage

    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
    󰡕
    0.46
    </bbox>
    0.46
    ер
    0.44
    ໃຫ້
    0.43
    <unused57>
    0.43
     бло
    0.43
     우리의
    0.41
    文件的
    0.41
     квартиру
    0.41
     मुस्
    0.41
    POSITIVE LOGITS
    ?
    0.48
    |
    0.46
    Upgrade
    0.45
    Summer
    0.43
     numar
    0.42
     nummer
    0.42
    .
    0.42
     number
    0.42
    وج
    0.42
    react
    0.42
    Activations Density 0.000%

    No Known Activations