© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203547
    Prev
    Next
    INDEX
    Explanations

    filed under

    np_acts-logits-general · gemini-2.5-flash-lite

    Here are lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    For
    0.49
    Very
    0.49
     For
    0.46
     .
    0.45
    ו
    0.45
     compromised
    0.44
    very
    0.44
     Very
    0.44
    Only
    0.44
    те
    0.44
    POSITIVE LOGITS
     merhabalar
    0.59
    rategy
    0.46
     ormai
    0.46
    ༻
    0.45
    র্গে
    0.45
     Donate
    0.44
     andDevice
    0.43
    </h3>
    0.42
     merhaba
    0.42
     hạnh
    0.41
    Activations Density 0.001%

    No Known Activations