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. 31-GEMMASCOPE-2-RES-16K
    4. 12820
    Prev
    Next
    INDEX
    Explanations

    names, concepts, history

    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_16k_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
     confir
    0.48
     single
    0.46
    ,
    0.46
     celestial
    0.45
     sculptural
    0.45
     specific
    0.44
     Welch
    0.44
     hela
    0.44
     *
    0.44
     terminal
    0.44
    POSITIVE LOGITS
    יל
    0.69
    𝘆
    0.61
    ма
    0.60
    리
    0.60
    ཥ
    0.59
    스
    0.59
    Makanan
    0.58
    רו
    0.57
    אי
    0.57
    드
    0.57
    Activations Density 0.781%

    No Known Activations