© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35059
    Prev
    Next
    INDEX
    Explanations

    how terms are referred to

    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_40_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
     znači
    0.45
     znamená
    0.42
    ፍ
    0.40
    অর্থ
    0.37
    Interpretation
    0.37
     zerstört
    0.37
    正好
    0.37
     betekent
    0.37
     previsto
    0.37
    悹
    0.37
    POSITIVE LOGITS
     refer
    0.95
     referring
    0.95
     Referring
    0.95
    refer
    0.89
     talking
    0.86
    Referring
    0.81
     Refer
    0.80
     referred
    0.78
     discussing
    0.77
    Refer
    0.76
    Activations Density 0.030%

    No Known Activations