© 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. 88279
    Prev
    Next
    INDEX
    Explanations

    Raspberry though

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

    global collaboration, binary tree, systems

    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
     clientele
    0.42
     kunder
    0.40
     ambience
    0.40
     pune
    0.40
     तट
    0.40
     utenti
    0.40
    霎
    0.40
     nostalg
    0.39
     pero
    0.39
    торию
    0.39
    POSITIVE LOGITS
    因為
    0.47
    adolid
    0.45
    名字
    0.44
    CMAKE
    0.43
    由於
    0.42
    tugraz
    0.42
    явить
    0.41
     Heisenberg
    0.40
    ),[
    0.40
    来进行
    0.39
    Activations Density 0.000%

    No Known Activations