© 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. 67431
    Prev
    Next
    INDEX
    Explanations

    no instance found

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

    no documented records

    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
     অনুভূত
    0.50
     почув
    0.49
     महसूस
    0.47
     অনুভব
    0.47
     क्योंकि
    0.42
     |”
    0.41
     ></
    0.40
     відчу
    0.40
    িও
    0.40
     |_
    0.39
    POSITIVE LOGITS
     nenhuma
    0.60
     jedin
    0.53
     aucune
    0.52
     nenhum
    0.52
     ningún
    0.49
    少なくとも
    0.49
     einzige
    0.49
     aucun
    0.48
     almeno
    0.48
     instances
    0.47
    Activations Density 0.095%

    No Known Activations