© 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. 240561
    Prev
    Next
    INDEX
    Explanations

    shoulder and strength

    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
    XmlApplication
    0.53
     язы
    0.50
    鱻
    0.48
     станови
    0.48
     पाइ
    0.47
    થમ
    0.47
    पहले
    0.46
     мест
    0.45
    ulfanyl
    0.45
    AnimationFrame
    0.44
    POSITIVE LOGITS
     monitors
    0.51
    shoulder
    0.50
     I
    0.48
     Mire
    0.47
     proven
    0.46
    song
    0.46
     shoulder
    0.45
     floating
    0.45
    songs
    0.45
     congrat
    0.45
    Activations Density 0.001%

    No Known Activations