© 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. 49048
    Prev
    Next
    INDEX
    Explanations

    phpFreeChat, traveling, providentially, dropped, button, Saturday

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

    checking preferences

    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
    HAM
    0.46
    have
    0.44
    CLAIM
    0.44
    του
    0.43
    МА
    0.43
    Atlet
    0.42
    ATH
    0.42
    름
    0.42
    AKER
    0.42
    UDE
    0.41
    POSITIVE LOGITS
     ስለዚህ
    0.50
     করার
    0.49
    হীন
    0.49
     понрави
    0.49
     dà
    0.48
     लौ
    0.48
     ficou
    0.48
    licos
    0.48
     negar
    0.47
    立った
    0.47
    Activations Density 0.000%

    No Known Activations