© 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. 19952
    Prev
    Next
    INDEX
    Explanations

    first derivative

    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
     Breed
    0.52
    峮
    0.44
     १००
    0.44
    breed
    0.43
    azione
    0.43
    uyendo
    0.43
     पीरियड
    0.43
    Breed
    0.42
    𒌨
    0.42
    Під
    0.41
    POSITIVE LOGITS
     instituições
    0.42
     alkenyl
    0.41
     transcribe
    0.41
     unsteady
    0.41
     constituents
    0.40
     interstitial
    0.39
     nonprofits
    0.39
     transient
    0.39
     nonlocal
    0.39
     experiment
    0.38
    Activations Density 0.000%

    No Known Activations