© 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. 14009
    Prev
    Next
    INDEX
    Explanations

    technical citations and identifiers

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

    entery or update

    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
    ໃຫ້
    0.43
    Pessoal
    0.42
    ന്ത്ര
    0.41
     iniciativas
    0.40
    สื่อ
    0.40
    靝
    0.40
     hardships
    0.40
    ന്വേഷ
    0.40
     olympi
    0.40
    ເຈ
    0.40
    POSITIVE LOGITS
     modem
    0.57
     Modem
    0.55
    ٠
    0.54
     Figure
    0.52
    0
    0.52
     F
    0.51
     J
    0.51
    }
    0.51
    j
    0.51
     E
    0.50
    Activations Density 0.025%

    No Known Activations