© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28355
    Prev
    Next
    INDEX
    Explanations

    code punctuation and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plas
    0.41
     Wherever
    0.40
    фт
    0.39
     Snakes
    0.38
     Plasma
    0.38
     Preferably
    0.38
    </iframe>
    0.37
     Maybe
    0.37
     ghép
    0.37
    courts
    0.37
    POSITIVE LOGITS
     bisogno
    0.46
     behov
    0.46
     necesitamos
    0.46
     potreb
    0.45
    醛
    0.45
     escánd
    0.42
     delito
    0.42
     regering
    0.42
     esenciales
    0.42
     esperado
    0.40
    Activations Density 0.082%

    No Known Activations