© 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. 15114
    Prev
    Next
    INDEX
    Explanations

    insane closest increasing

    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
     confirmed
    0.48
     Q
    0.47
     risk
    0.46
     COVID
    0.46
     topped
    0.46
     Fight
    0.46
     consolid
    0.45
     validated
    0.44
     tumor
    0.44
     CNN
    0.43
    POSITIVE LOGITS
    apabb
    0.59
    𝒐
    0.52
    𝙷
    0.49
    drv
    0.48
    sime
    0.47
    ayutt
    0.47
     देत
    0.46
    thisStudent
    0.46
    ák
    0.46
    }:${
    0.46
    Activations Density 0.008%

    No Known Activations