© 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. 180778
    Prev
    Next
    INDEX
    Explanations

    like eye

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

    action and continuation

    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
    當地
    0.52
    並不
    0.50
     sinnvoll
    0.50
     deutschen
    0.49
     液
    0.48
     Pd
    0.47
     ganar
    0.47
    ចាំ
    0.47
    LastGen
    0.47
     MAP
    0.46
    POSITIVE LOGITS
    ỏa
    0.52
    وید
    0.44
    온
    0.42
    イレ
    0.42
    پر
    0.41
     знаком
    0.41
    ኳ
    0.41
     کول
    0.40
     terl
    0.40
    да
    0.40
    Activations Density 0.000%

    No Known Activations