© 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. 9559
    Prev
    Next
    INDEX
    Explanations

    of people, same thing

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

    Goal, Agent, Materials, Symptoms

    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
     appointment
    0.48
     another
    0.47
     things
    0.46
    :
    0.46
     batches
    0.45
     lots
    0.45
     appointments
    0.45
     loans
    0.44
     to
    0.44
     ANOTHER
    0.43
    POSITIVE LOGITS
    zględ
    0.56
    餚
    0.50
     capitaine
    0.49
    aguchi
    0.48
    desIP
    0.48
    ribe
    0.47
     tighten
    0.47
    𝐤
    0.47
    marshalO
    0.46
    ায়ক
    0.46
    Activations Density 0.000%

    No Known Activations