© 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. 51516
    Prev
    Next
    INDEX
    Explanations

    legal, medical, or computational terms

    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
     முது
    0.41
    ┴
    0.39
    Correction
    0.38
     لنک
    0.38
    Proble
    0.37
    proble
    0.37
    jsonwebtoken
    0.37
    Jwt
    0.36
    խ
    0.36
    блема
    0.36
    POSITIVE LOGITS
     bunkers
    0.43
     burials
    0.41
     nomadic
    0.41
     arraigned
    0.41
     số
    0.40
     நிர்வாக
    0.40
     briefs
    0.40
     vuelos
    0.40
     affidavits
    0.39
     erections
    0.39
    Activations Density 0.029%

    No Known Activations