© 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. 66594
    Prev
    Next
    INDEX
    Explanations

    time will

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

    tend to / need to / ability to

    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
    sine
    0.56
    a
    0.48
    is
    0.47
    activating
    0.46
    buffer
    0.46
    ag
    0.45
    outputs
    0.44
     annuities
    0.44
    λικό
    0.44
     accelerating
    0.44
    POSITIVE LOGITS
    다
    0.49
     که
    0.48
     ویکی
    0.47
     kullanılır
    0.46
    꾸
    0.46
     पुलिस
    0.46
     ещё
    0.45
    PreviewSize
    0.45
    のだ
    0.45
    ției
    0.45
    Activations Density 0.001%

    No Known Activations