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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18719
    Prev
    Next
    INDEX
    Explanations

    granting, allowing, or discouraging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    0.44
    -
    0.41
    a
    0.40
    酷
    0.39
    <0x85>
    0.39
    त्ता
    0.39
    ophilus
    0.39
    禮
    0.39
    пас
    0.39
    在
    0.39
    POSITIVE LOGITS
     Ormond
    0.52
     Agro
    0.48
     citing
    0.47
     aiut
    0.47
    Comunic
    0.47
     hostilities
    0.46
     arrib
    0.46
    ursery
    0.46
     aident
    0.46
    Ana
    0.45
    Activations Density 0.001%

    No Known Activations