© 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. 233181
    Prev
    Next
    INDEX
    Explanations

    maximizing growth, artistic designs, negative effects

    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
     estrogens
    0.55
     laurea
    0.52
    quando
    0.51
    🕶
    0.51
     kalor
    0.50
     calorías
    0.49
     quando
    0.49
     calories
    0.49
    calorie
    0.48
     menurun
    0.48
    POSITIVE LOGITS
    셰
    0.46
    elos
    0.42
    PU
    0.42
     Consortium
    0.42
    ક્ત
    0.42
    umna
    0.41
    診
    0.41
    olved
    0.40
    testers
    0.40
     Battle
    0.40
    Activations Density 0.001%

    No Known Activations