© 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. 93837
    Prev
    Next
    INDEX
    Explanations

    cryptographic keys, actions

    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
    ді
    0.49
    ють
    0.44
    ﮟ
    0.44
    Mic
    0.42
    مانی
    0.41
    ਸ
    0.41
    рі
    0.41
    채
    0.41
     mic
    0.40
    вають
    0.40
    POSITIVE LOGITS
    ptions
    0.54
    erapia
    0.50
     varphi
    0.50
    nson
    0.48
    zuf
    0.48
    aries
    0.48
    rypt
    0.47
    trs
    0.47
    rison
    0.47
     Кы
    0.46
    Activations Density 0.002%

    No Known Activations