Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119929
    Prev
    Next
    INDEX
    Explanations

    gorillas, masks, mental, subtly

    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
     elects
    0.40
     अपॉन
    0.40
    Με
    0.40
    Β
    0.39
     Π
    0.39
    आईपी
    0.38
    륨
    0.38
    amless
    0.38
     MEANS
    0.38
    Π
    0.38
    POSITIVE LOGITS
     nan
    0.44
     frustrations
    0.40
     nano
    0.39
     num
    0.38
     support
    0.38
     perhaps
    0.38
     question
    0.38
     rotors
    0.38
     normal
    0.37
     pensando
    0.37
    Activations Density 0.000%

    No Known Activations