© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193026
    Prev
    Next
    INDEX
    Explanations

    clinical practice, schoolgirls, github, critical infrastructure, Witch Cults, model

    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_40_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
    巳
    0.46
    Ved
    0.44
    𝗚
    0.42
    symmetric
    0.41
    浬
    0.41
    TextMessage
    0.41
    एसएल
    0.40
     kttt
    0.40
    閎
    0.40
     Unlimited
    0.39
    POSITIVE LOGITS
     peter
    0.39
    震惊
    0.38
     shocked
    0.37
     disebut
    0.37
     Oxidation
    0.36
    shock
    0.36
    angor
    0.35
     frag
    0.35
    lette
    0.35
    Directions
    0.34
    Activations Density 0.000%

    No Known Activations