© 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. 4158
    Prev
    Next
    INDEX
    Explanations

    returning values

    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
    ಕ್ಕಿಂತ
    0.30
     фаразлау
    0.27
     ikke
    0.27
     skapa
    0.26
    <unused1865>
    0.26
     ekki
    0.25
     nicht
    0.25
     نہيں
    0.25
     לא
    0.25
    以外の
    0.25
    POSITIVE LOGITS
    b
    0.32
    d
    0.30
    /
    0.26
    #
    0.25
    ap
    0.25
    -
    0.25
    ↵↵
    0.24
    nin
    0.24
    У
    0.24
    f
    0.24
    Activations Density 0.158%

    No Known Activations