© 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. 154961
    Prev
    Next
    INDEX
    Explanations

    deals and services

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

    harder to guess

    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
    醾
    0.55
    ваемых
    0.51
    ुल
    0.50
    уы
    0.50
     injurious
    0.48
     failings
    0.46
    Ⲥ
    0.45
     griev
    0.45
     Cited
    0.45
    ियोग्राफी
    0.45
    POSITIVE LOGITS
    Photon
    0.48
     hidrógeno
    0.47
     )
    0.46
    apparent
    0.46
     některé
    0.45
    state
    0.45
     Neuron
    0.45
     sûr
    0.45
     stof
    0.45
     zwei
    0.44
    Activations Density 0.001%

    No Known Activations