© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17993
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
    પ
    0.44
    Để
    0.43
     фаразлау
    0.42
    Everything
    0.42
    Vậy
    0.41
    р
    0.41
    IGet
    0.40
    LJ
    0.39
    Bj
    0.39
    Eff
    0.39
    POSITIVE LOGITS
     (%
    0.49
     (=
    0.45
     (−
    0.45
     (>
    0.45
     (
    0.44
     this
    0.42
     ($
    0.41
    0.41
     rudder
    0.41
     questo
    0.40
    Activations Density 0.010%

    No Known Activations