© 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. 206135
    Prev
    Next
    INDEX
    Explanations

    investment, reporting, government, hacking

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

    encrypted data

    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
    \
    0.53
     .
    0.49
     rejected
    0.49
     portions
    0.49
     quanto
    0.48
    כול
    0.47
     inserted
    0.47
    \...
    0.46
    …
    0.46
    ...')
    0.46
    POSITIVE LOGITS
    triple
    0.49
    iveau
    0.47
     abusing
    0.46
    straat
    0.45
     überprüfen
    0.45
    brauch
    0.43
    attacking
    0.43
     Konzept
    0.42
    ንዳንድ
    0.42
    ॉफ्ट
    0.42
    Activations Density 0.001%

    No Known Activations