© 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. 71613
    Prev
    Next
    INDEX
    Explanations

    payment terms

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

    sequences before specific follow-ups

    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
    ли
    0.64
     ocurr
    0.48
    ের
    0.48
    LO
    0.47
     abril
    0.47
    ници
    0.46
    ].
    0.46
     sido
    0.46
     avea
    0.46
    юнча
    0.46
    POSITIVE LOGITS
     документы
    0.43
    newTask
    0.42
    ٧
    0.42
     smartphone
    0.41
    StartTime
    0.41
     مدرسه
    0.41
     موسم
    0.40
     Stéphane
    0.40
    currentTime
    0.40
    trashButton
    0.40
    Activations Density 0.001%

    No Known Activations