© 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. 2914
    Prev
    Next
    INDEX
    Explanations

    this is followed by statement

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

    this is a tricky question

    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
    这两个
    0.36
     här
    0.33
     aient
    0.32
     esistono
    0.32
    RUP
    0.31
    这两
    0.31
     छन्
    0.31
    鳝
    0.30
     这些
    0.30
     étrang
    0.30
    POSITIVE LOGITS
     happens
    0.42
     happened
    0.41
     merupakan
    0.41
     રીતે
    0.39
     happen
    0.37
     tantamount
    0.36
     happening
    0.36
     ocurrió
    0.36
    resultado
    0.35
     remedied
    0.35
    Activations Density 0.463%

    No Known Activations