© 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. 31-GEMMASCOPE-2-RES-262K
    7. 123362
    Prev
    Next
    INDEX
    Explanations

    dates, network, simple, non-invasive

    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
    pitch
    0.46
    ts
    0.46
    ities
    0.46
     configuration
    0.44
     pitch
    0.43
    pitched
    0.42
    human
    0.42
    g
    0.42
    of
    0.41
    с
    0.41
    POSITIVE LOGITS
    珽
    0.48
     niž
    0.48
     eosin
    0.47
     včetně
    0.47
    ।--
    0.47
    öö
    0.46
     transfert
    0.46
     Faktoren
    0.44
     Resting
    0.44
    度假
    0.44
    Activations Density 0.004%

    No Known Activations