© 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. 138000
    Prev
    Next
    INDEX
    Explanations

    years, five

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

    South Park Metaverse Meltdown

    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
     debilitating
    0.52
     crippling
    0.52
     conflic
    0.51
     burdensome
    0.49
     reç
    0.47
     욕
    0.47
     eo
    0.47
     verifica
    0.46
     restricciones
    0.46
     risiko
    0.46
    POSITIVE LOGITS
    gp
    0.53
    giveness
    0.49
    ฟา
    0.49
    জ
    0.49
    ക്കുള്ള
    0.48
    imgur
    0.46
    簡単
    0.45
    زه
    0.45
    比較
    0.45
    पर्स
    0.45
    Activations Density 0.000%

    No Known Activations