© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45988
    Prev
    Next
    INDEX
    Explanations

    situational clauses

    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_65k_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
    ເທ
    0.46
    ^*_{
    0.40
     постепенно
    0.40
    ěž
    0.39
     அவர்க
    0.39
     ভয়ঙ্কর
    0.39
    イス
    0.39
    iglia
    0.38
    ἱ
    0.38
    ѝ
    0.38
    POSITIVE LOGITS
     vann
    0.49
     Trans
    0.45
     atoms
    0.44
     sayesinde
    0.43
     Inline
    0.43
     yeni
    0.42
    Neurons
    0.41
    दत
    0.41
     inc
    0.41
     atom
    0.41
    Activations Density 0.003%

    No Known Activations