© 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. 136062
    Prev
    Next
    INDEX
    Explanations

    mother's voice

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

    describing quantity or state

    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
    pools
    0.46
     сопрово
    0.46
     Coatings
    0.46
    ulai
    0.44
    apers
    0.44
    benar
    0.44
    ک
    0.44
     होईल
    0.43
    paren
    0.43
    ")]
    0.43
    POSITIVE LOGITS
     εύ
    0.50
     torso
    0.50
     NEED
    0.49
     kroner
    0.47
     debacle
    0.46
     grasping
    0.46
     WITHOUT
    0.46
     clutching
    0.46
     nắm
    0.45
     DURING
    0.45
    Activations Density 0.001%

    No Known Activations