© 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-65K
    7. 50815
    Prev
    Next
    INDEX
    Explanations

    authenticity and identity

    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_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
    TimeDict
    0.41
    спекти
    0.39
    梦想
    0.39
    Healthy
    0.38
    鋆
    0.38
    kers
    0.38
    Kraft
    0.36
     Healthy
    0.36
    夢
    0.36
    ఠ
    0.36
    POSITIVE LOGITS
     identity
    1.16
    identity
    1.05
     Identity
    1.05
     identidad
    1.05
    Identity
    1.01
     Who
    0.96
     who
    0.95
     quién
    0.92
    identité
    0.91
     identidade
    0.90
    Activations Density 0.095%

    No Known Activations