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. 16-GEMMASCOPE-2-RES-262K
    4. 86385
    Prev
    Next
    INDEX
    Explanations

    python pip installs and rust mut refs

    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_16_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
     titoli
    0.48
    <0x80>
    0.43
    H
    0.42
    ಾರ
    0.38
     belladone
    0.37
     documenti
    0.37
    ٨
    0.37
     hanno
    0.36
     нова
    0.36
    ᅪ
    0.35
    POSITIVE LOGITS
     in
    0.77
    s
    0.51
    在
    0.49
    .
    0.47
    ی
    0.47
    self
    0.46
    ים
    0.44
    ın
    0.44
    ssystem
    0.43
    ের
    0.42
    Activations Density 0.000%

    No Known Activations