© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2761
    Prev
    Next
    INDEX
    Explanations

    weekday evening and indicator light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     везде
    1.56
     вся
    1.51
     общей
    1.51
     CIRCUIT
    1.50
     какво
    1.50
     各
    1.47
    TAC
    1.47
    弘
    1.45
    }:=\
    1.45
    违法
    1.45
    POSITIVE LOGITS
    ers
    1.34
    erset
    1.10
    aught
    1.05
     iteration
    0.97
    nou
    0.96
    reve
    0.90
    sworth
    0.89
    atch
    0.89
    erson
    0.89
    oms
    0.89
    Activations Density 0.000%

    No Known Activations