© 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. 162052
    Prev
    Next
    INDEX
    Explanations

    claim, anesthesia, means, bit, small, choose

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

    definitions, actions, and topics

    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
    hé
    0.51
    ahu
    0.48
     lampu
    0.47
    es
    0.47
     רו
    0.46
    ه
    0.45
    מו
    0.45
    ering
    0.45
    (=
    0.45
    Decrement
    0.45
    POSITIVE LOGITS
     defines
    0.49
     simplifies
    0.49
     locates
    0.48
     దీని
    0.46
     predstavlja
    0.46
     prohibits
    0.46
     termine
    0.45
     qualifies
    0.45
     aligns
    0.44
    ILITIES
    0.44
    Activations Density 0.002%

    No Known Activations