© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220115
    Prev
    Next
    INDEX
    Explanations

    dealing with complexity

    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
    Negative Logits
     Ú
    0.42
    adoff
    0.39
    脇
    0.39
     behavioural
    0.39
    abilidad
    0.38
     INCIDENTAL
    0.38
     escalation
    0.38
     compre
    0.37
     bew
    0.37
     automáticamente
    0.37
    POSITIVE LOGITS
     질문
    0.48
    issam
    0.40
    空氣
    0.40
    質問
    0.39
     χρόνο
    0.37
    占
    0.36
     sheets
    0.36
     നിന്നും
    0.36
     Trusted
    0.36
    ה
    0.35
    Activations Density 0.000%

    No Known Activations