© 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. 145577
    Prev
    Next
    INDEX
    Explanations

    doughnuts, same team, applicable

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

    exploitation of characters

    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
    ?]
    0.56
    ?
    0.56
            
    0.54
    0.50
    ]
    0.49
    <0x0D>
    0.48
     inflam
    0.48
     impeachment
    0.46
     reac
    0.45
     imput
    0.45
    POSITIVE LOGITS
    好き
    0.52
    ഫി
    0.48
    APPROVED
    0.47
     Verhältnis
    0.47
    猢
    0.46
    推薦
    0.46
     последние
    0.45
    field
    0.45
     APPROVED
    0.44
    䡇
    0.44
    Activations Density 0.000%

    No Known Activations