© 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. 74112
    Prev
    Next
    INDEX
    Explanations

    looking for relationships

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

    back like a cat

    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
    ferm
    0.49
    slots
    0.49
    valve
    0.48
    ford
    0.48
     Pedagog
    0.48
     Cac
    0.47
    xg
    0.46
    嚥
    0.46
    Ped
    0.44
    Game
    0.44
    POSITIVE LOGITS
     দুর্ভাগ্য
    0.51
    ulfanyl
    0.47
     ಸಂಬಂಧ
    0.46
     comforted
    0.46
     stockfoto
    0.44
     regrett
    0.44
     શ્રે
    0.44
    ┻
    0.43
     governor
    0.43
    NullException
    0.42
    Activations Density 0.000%

    No Known Activations