© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4890
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     জঙ্গ
    0.71
    মাণ
    0.70
     Konst
    0.69
     मानवता
    0.68
    ROR
    0.66
    ಹಿತ
    0.65
    胤
    0.65
    PSA
    0.65
    мость
    0.64
    мули
    0.64
    POSITIVE LOGITS
    ⁴
    1.12
    ³
    1.05
    <sup>
    1.02
    ²,
    0.97
    ⁵
    0.94
    ²
    0.92
    .³
    0.92
    ⁶
    0.90
    ³.
    0.89
     squre
    0.89
    Activations Density 0.084%

    No Known Activations