© 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-262K
    7. 42848
    Prev
    Next
    INDEX
    Explanations

    companies, locations, and management

    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_262k_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
    衣服
    0.47
    ීමට
    0.46
    䖝
    0.45
    вів
    0.44
    Ꮑ
    0.42
    ்ப
    0.41
    帀
    0.40
    𝙫
    0.40
     kæ
    0.39
    NEUTRON
    0.39
    POSITIVE LOGITS
    operations
    0.46
     இழு
    0.46
     doświad
    0.44
    ac
    0.43
    /
    0.43
     rozpoczę
    0.43
     objeto
    0.42
    ew
    0.42
    cciones
    0.42
     einde
    0.42
    Activations Density 0.002%

    No Known Activations