© 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-262K
    7. 170203
    Prev
    Next
    INDEX
    Explanations

    code snippets and logic

    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_262k_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
    utente
    0.42
    November
    0.41
    ANCIAL
    0.40
    ristown
    0.40
    rasında
    0.40
    ంశ
    0.39
    㕣
    0.38
    informations
    0.38
    aw
    0.38
    aired
    0.38
    POSITIVE LOGITS
     a
    0.43
     carburetor
    0.41
     trypsin
    0.41
     interpol
    0.40
     suitable
    0.40
     aromat
    0.38
     culprit
    0.38
     baseline
    0.38
     pharmacological
    0.37
    合适的
    0.37
    Activations Density 0.014%

    No Known Activations