© 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. 120164
    Prev
    Next
    INDEX
    Explanations

    intensive and

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

    performance and operations

    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
    म्स
    0.46
    を見た
    0.44
     discredited
    0.43
     DISCLAIMED
    0.40
    ‐
    0.39
     systemic
    0.38
     قاعد
    0.38
    人に
    0.38
     Lemma
    0.38
     ಪ್ರಕರಣ
    0.37
    POSITIVE LOGITS
     equestrian
    0.46
     motorsport
    0.43
     photoshoot
    0.41
     eyewear
    0.40
     옷
    0.40
     sculptures
    0.40
     sculptural
    0.40
    प्टेंबर
    0.40
    टरीना
    0.39
     refurb
    0.39
    Activations Density 0.000%

    No Known Activations