© 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. 157407
    Prev
    Next
    INDEX
    Explanations

    concepts followed by details

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

    ASIL Determination

    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
     لماذا
    0.47
    㶪
    0.46
     уважа
    0.46
     strCmd
    0.44
     실험
    0.44
     extraño
    0.44
     э
    0.44
     strumenti
    0.44
     chargés
    0.44
     შეიძლება
    0.43
    POSITIVE LOGITS
    きちんと
    0.44
    一緒に
    0.44
    oh
    0.43
     Pinterest
    0.43
     Colonies
    0.43
     Argos
    0.42
    .
    0.42
    others
    0.42
    ised
    0.41
    分岐
    0.41
    Activations Density 0.000%

    No Known Activations