© 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-262K
    7. 12522
    Prev
    Next
    INDEX
    Explanations

    look for outward

    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
    Not in Any Lists

    No Comments

    Negative Logits
     restitu
    0.47
    环节
    0.44
     estan
    0.41
     iki
    0.40
     seleccionado
    0.40
     necesita
    0.40
     issus
    0.40
    ź
    0.39
     require
    0.39
    programa
    0.39
    POSITIVE LOGITS
    ward
    0.41
    ways
    0.39
    Ways
    0.38
    Chemistry
    0.37
     Ward
    0.37
    Strength
    0.37
     mg
    0.36
    !("
    0.36
    Statistical
    0.36
     Ways
    0.35
    Activations Density 0.000%

    No Known Activations