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

    Neuronpedia

    Jacobian LensNEW
    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. 4109
    Prev
    Next
    INDEX
    Explanations

    technical support or care

    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
    ర్
    0.45
     بُ
    0.41
    ुत
    0.41
    ፣
    0.40
     يُ
    0.40
    、「
    0.40
    𝒈
    0.40
    氦
    0.39
    supportsFocus
    0.39
    ้า
    0.39
    POSITIVE LOGITS
     nbsp
    0.68
     youre
    0.65
     doesnt
    0.63
     wasnt
    0.60
     youll
    0.60
     theyre
    0.57
     arent
    0.55
    mdash
    0.55
     isnt
    0.54
     couldnt
    0.52
    Activations Density 0.076%

    No Known Activations