© 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. 159038
    Prev
    Next
    INDEX
    Explanations

    service with a smile

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

    ShareGPT or his gambling

    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
     Cl
    0.51
    :
    0.50
     CO
    0.49
     Fluid
    0.49
     PERIOD
    0.48
     Angel
    0.46
     Swami
    0.46
     Periodic
    0.46
     Central
    0.46
     Function
    0.46
    POSITIVE LOGITS
    やつ
    0.52
    PAY
    0.51
    뺏
    0.51
    세
    0.50
    끅
    0.50
     tolerate
    0.49
    améli
    0.49
     vaccinate
    0.49
    Mist
    0.49
     đậu
    0.49
    Activations Density 0.000%

    No Known Activations