© 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. 223740
    Prev
    Next
    INDEX
    Explanations

    or even, gives you, this day

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

    their panties, particularly Cancun

    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
    は見
    0.54
    اي
    0.49
    一張
    0.46
    堅
    0.45
    懷
    0.44
     materiais
    0.44
    バース
    0.43
    見
    0.42
     மனித
    0.42
     förm
    0.42
    POSITIVE LOGITS
     coseno
    0.46
    ExtensionsPath
    0.43
     равна
    0.43
    ictionary
    0.42
    บท
    0.42
    Final
    0.42
    adir
    0.42
     consentimiento
    0.42
    atino
    0.42
    ana
    0.41
    Activations Density 0.001%

    No Known Activations