© 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. 81533
    Prev
    Next
    INDEX
    Explanations

    DIY, pet, candidate, skills

    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
    álov
    0.38
     ठर
    0.37
     unkind
    0.37
    [:
    0.35
    welcome
    0.35
     avoidable
    0.35
    avourable
    0.35
    گز
    0.34
     reactance
    0.34
    insic
    0.34
    POSITIVE LOGITS
    銅
    0.43
    鈞
    0.42
     batteria
    0.40
     पाइप
    0.39
     आरबीआई
    0.39
     besser
    0.38
    icleta
    0.38
     médica
    0.38
     LOGGER
    0.38
    鵝
    0.38
    Activations Density 0.004%

    No Known Activations