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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 639
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     If
    0.39
     efet
    0.38
     explic
    0.37
     It
    0.35
    ق
    0.35
     der
    0.34
     atual
    0.34
     always
    0.34
     aloof
    0.33
     interação
    0.33
    POSITIVE LOGITS
    hz
    0.51
    +
    0.49
    ua
    0.46
    ha
    0.46
    9
    0.44
    us
    0.44
    round
    0.44
    jande
    0.44
    hl
    0.41
    5
    0.40
    Activations Density 0.326%

    No Known Activations