© 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. 33787
    Prev
    Next
    INDEX
    Explanations

    Apple computer, weekly grocery

    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
    ekyll
    0.39
     destination
    0.39
     domestic
    0.39
     $(
    0.38
     summer
    0.38
     photographic
    0.38
     charm
    0.38
     vign
    0.37
     destino
    0.36
     jubil
    0.36
    POSITIVE LOGITS
    Aim
    0.48
    Probability
    0.44
    People
    0.43
    }=-\
    0.42
    ާއ
    0.42
    Раз
    0.41
    Updated
    0.40
    Interactive
    0.39
    advers
    0.39
    الن
    0.38
    Activations Density 0.000%

    No Known Activations