© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4627
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility or speculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    occa
    0.44
    pretty
    0.42
    closes
    0.42
    á
    0.40
    advantages
    0.40
     кам
    0.40
    ure
    0.39
    binary
    0.39
     облада
    0.39
    ă
    0.39
    POSITIVE LOGITS
     prolet
    0.48
     hiss
    0.46
    ,))
    0.46
    प्रिय
    0.46
     fervor
    0.45
     pach
    0.44
     vytvá
    0.44
     secession
    0.44
    ，
    0.43
     mieszkańców
    0.43
    Activations Density 0.000%

    No Known Activations