© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61836
    Prev
    Next
    INDEX
    Explanations

    biological or technical connections

    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
    ling
    0.50
    aci
    0.48
    ato
    0.48
    arella
    0.48
    0
    0.48
    italic
    0.45
    Lc
    0.45
    ett
    0.44
    dic
    0.44
    het
    0.44
    POSITIVE LOGITS
     commuters
    0.46
     manganese
    0.45
     Chayin
    0.45
     precincts
    0.45
     ព
    0.44
     korban
    0.44
     depths
    0.44
     tajem
    0.43
     amperes
    0.43
     lidí
    0.43
    Activations Density 0.011%

    No Known Activations