© 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-262K
    7. 54339
    Prev
    Next
    INDEX
    Explanations

    protection, survival, neutrality

    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_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
    B
    0.49
    L
    0.45
    R
    0.45
     four
    0.44
    D
    0.44
    A
    0.44
     nine
    0.44
     three
    0.44
    T
    0.43
    October
    0.43
    POSITIVE LOGITS
     sofá
    0.48
     teclas
    0.47
    釭
    0.46
    防护
    0.46
     risking
    0.46
     birdseye
    0.44
    偶尔
    0.44
     cops
    0.44
     douche
    0.43
    ättre
    0.43
    Activations Density 0.010%

    No Known Activations