© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 119494
    Prev
    Next
    INDEX
    Explanations

    programming and descriptions

    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
    eos
    0.50
     သည်
    0.41
     अर्चना
    0.40
     Tsuen
    0.39
    ှ
    0.38
     ос
    0.37
    łoś
    0.37
    `(
    0.37
     sovr
    0.37
    úz
    0.37
    POSITIVE LOGITS
     Computation
    0.44
    Plot
    0.39
     SISO
    0.38
    Heading
    0.38
    Sketch
    0.37
    Searching
    0.37
    꽉
    0.37
     dismissing
    0.37
    imha
    0.37
    Alarm
    0.36
    Activations Density 0.000%

    No Known Activations