© 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. 226209
    Prev
    Next
    INDEX
    Explanations

    when

    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
    맘
    0.50
    路撒
    0.49
     اقول
    0.46
     гале
    0.46
     Bowls
    0.44
    }}^{*
    0.42
     консу
    0.42
    主力
    0.40
     અપ
    0.40
    }=(
    0.39
    POSITIVE LOGITS
     when
    0.56
    when
    0.51
     ketika
    0.51
     때
    0.50
     når
    0.49
     когда
    0.49
     când
    0.48
     när
    0.48
    también
    0.48
    ma
    0.47
    Activations Density 0.002%

    No Known Activations