© 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. 29708
    Prev
    Next
    INDEX
    Explanations

    acidic variations

    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
    лі
    0.50
    ል
    0.50
     ovens
    0.48
    keits
    0.44
    დ
    0.43
    浧
    0.43
     closets
    0.42
    ད
    0.42
    цію
    0.42
    nias
    0.42
    POSITIVE LOGITS
     personer
    0.52
     during
    0.50
    vDash
    0.44
     consecutively
    0.44
    unpack
    0.43
     retrieved
    0.43
     interpret
    0.42
     improperly
    0.42
     inputted
    0.42
     Hd
    0.41
    Activations Density 0.002%

    No Known Activations